From eb4fffbbf445b7a7b7909b27c77b445850d72012 Mon Sep 17 00:00:00 2001 From: "Philip.Hazel" Date: Fri, 21 Nov 2014 16:45:06 +0000 Subject: [PATCH] More documentation and file tidies. --- CMakeLists.txt | 2 +- RunTest | 2 +- doc/html/pcre2.html | 19 +- doc/html/pcre2api.html | 395 ++++++----- doc/html/pcre2build.html | 2 +- doc/html/pcre2callout.html | 2 +- doc/html/pcre2compat.html | 2 +- doc/html/pcre2grep.html | 2 +- doc/html/pcre2jit.html | 2 +- doc/html/pcre2limits.html | 2 +- doc/html/pcre2matching.html | 2 +- doc/html/pcre2partial.html | 2 +- doc/html/pcre2pattern.html | 2 +- doc/html/pcre2perform.html | 2 +- doc/html/pcre2posix.html | 2 +- doc/html/pcre2sample.html | 2 +- doc/html/pcre2stack.html | 16 +- doc/html/pcre2syntax.html | 2 +- doc/html/pcre2test.html | 2 +- doc/html/pcre2unicode.html | 2 +- doc/pcre2.3 | 2 +- doc/pcre2.txt | 1333 ++++++++++++++++++----------------- doc/pcre2api.3 | 176 ++--- src/pcre2_jit_compile.c | 6 +- src/pcre2_match.c | 8 +- 25 files changed, 1002 insertions(+), 987 deletions(-) diff --git a/CMakeLists.txt b/CMakeLists.txt index 6e65cee..8f944df 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -394,7 +394,7 @@ SET(PCRE2_SOURCES src/pcre2_pattern_info.c src/pcre2_string_utils.c src/pcre2_study.c - src/pcre2_substitute.c + src/pcre2_substitute.c src/pcre2_substring.c src/pcre2_tables.c src/pcre2_ucd.c diff --git a/RunTest b/RunTest index 8f6d0a0..6ed2017 100755 --- a/RunTest +++ b/RunTest @@ -286,7 +286,7 @@ if [ $? -eq 0 ] ; then test2stack="-S 16" else test2stack="" -fi +fi # All of 8-bit, 16-bit, and 32-bit character strings may be supported, but only # one need be. diff --git a/doc/html/pcre2.html b/doc/html/pcre2.html index 0f6f83d..a01c63f 100644 --- a/doc/html/pcre2.html +++ b/doc/html/pcre2.html @@ -25,9 +25,10 @@ PCRE2 is the name used for a revised API for the PCRE library, which is a set of functions, written in C, that implement regular expression pattern matching using the same syntax and semantics as Perl, with just a few differences. Some features that appeared in Python and the original PCRE before they appeared in -Perl are also available using the Python syntax, there is some support for one -or two .NET and Oniguruma syntax items, and there are options for requesting -some minor changes that give better ECMAScript (aka JavaScript) compatibility. +Perl are also available using the Python syntax. There is also some support for +one or two .NET and Oniguruma syntax items, and there are options for +requesting some minor changes that give better ECMAScript (aka JavaScript) +compatibility.

The source code for PCRE2 can be compiled to support 8-bit, 16-bit, or 32-bit @@ -36,7 +37,7 @@ The original work to extend PCRE to 16-bit and 32-bit code units was done by Zoltan Herczeg and Christian Persch, respectively. In all three cases, strings can be interpreted either as one character per code unit, or as UTF-encoded Unicode, with support for Unicode general category properties. Unicode support -is optional at build time (but is the default); however, processing strings as +is optional at build time (but is the default). However, processing strings as UTF code units must be enabled explicitly at run time. The version of Unicode in use can be discovered by running 

@@ -143,17 +144,17 @@ listing), and the short pages for individual functions, are concatenated in
   pcre2compat        discussion of Perl compatibility
   pcre2demo          a demonstration C program that uses PCRE2
   pcre2grep          description of the pcre2grep command (8-bit only)
-  pcre2jit           discussion of the just-in-time optimization support
+  pcre2jit           discussion of just-in-time optimization support
   pcre2limits        details of size and other limits
   pcre2matching      discussion of the two matching algorithms
   pcre2partial       details of the partial matching facility
-  pcre2pattern       syntax and semantics of supported regular expressions
+  pcre2pattern       syntax and semantics of supported regular  expression patterns
   pcre2perform       discussion of performance issues
   pcre2posix         the POSIX-compatible C API for the 8-bit library
   pcre2sample        discussion of the pcre2demo program
   pcre2stack         discussion of stack usage
   pcre2syntax        quick syntax reference
-  pcre2test          description of the pcre2test testing command
+  pcre2test          description of the pcre2test command
   pcre2unicode       discussion of Unicode and UTF support
In the "man" and HTML formats, there is also a short page for each C library @@ -165,7 +166,7 @@ Philip Hazel
University Computing Service
-Cambridge CB2 3QH, England. +Cambridge, England.

@@ -174,7 +175,7 @@ use my two initials, followed by the two digits 10, at the domain cam.ac.uk.


REVISION

-Last updated: 03 November 2014 +Last updated: 18 November 2014
Copyright © 1997-2014 University of Cambridge.
diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index bbb329e..ef3ac2a 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -37,16 +37,18 @@ please consult the man page, in case the conversion went wrong.

  • MATCHING A PATTERN: THE TRADITIONAL FUNCTION
  • NEWLINE HANDLING WHEN MATCHING
  • HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS -
  • EXTRACTING CAPTURED SUBSTRINGS BY NUMBER -
  • EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS -
  • EXTRACTING CAPTURED SUBSTRINGS BY NAME -
  • CREATING A NEW STRING WITH SUBSTITUTIONS -
  • DUPLICATE SUBPATTERN NAMES -
  • FINDING ALL POSSIBLE MATCHES -
  • MATCHING A PATTERN: THE ALTERNATIVE FUNCTION -
  • SEE ALSO -
  • AUTHOR -
  • REVISION +
  • OTHER INFORMATION ABOUT A MATCH +
  • ERROR RETURNS FROM pcre2_match() +
  • EXTRACTING CAPTURED SUBSTRINGS BY NUMBER +
  • EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS +
  • EXTRACTING CAPTURED SUBSTRINGS BY NAME +
  • CREATING A NEW STRING WITH SUBSTITUTIONS +
  • DUPLICATE SUBPATTERN NAMES +
  • FINDING ALL POSSIBLE MATCHES AT ONE POSITION +
  • MATCHING A PATTERN: THE ALTERNATIVE FUNCTION +
  • SEE ALSO +
  • AUTHOR +
  • REVISION

    #include <pcre2.h> @@ -436,13 +438,9 @@ U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS

    Each of the first three conventions is used by at least one operating system as its standard newline sequence. When PCRE2 is built, a default can be specified. -The default default is LF, which is the Unix standard. When PCRE2 is run, the -default can be overridden, either when a pattern is compiled, or when it is -matched. -

    -

    -The newline convention can be changed when calling pcre2_compile(), or it -can be specified by special text at the start of the pattern itself; this +The default default is LF, which is the Unix standard. However, the newline +convention can be changed by an application when calling pcre2_compile(), +or it can be specified by special text at the start of the pattern itself; this overrides any other settings. See the pcre2pattern page for details of the special character sequences. @@ -459,8 +457,8 @@ below.

    The choice of newline convention does not affect the interpretation of -the \n or \r escape sequences, nor does it affect what \R matches, which has -its own separate control. +the \n or \r escape sequences, nor does it affect what \R matches; this has +its own separate convention.


    MULTITHREADING

    @@ -472,7 +470,7 @@ time ensuring that multithreaded applications can use it.

    There are several different blocks of data that are used to pass information -between the application and the PCRE libraries. +between the application and the PCRE2 libraries.

    (1) A pointer to the compiled form of a pattern is returned to the user when @@ -572,11 +570,11 @@ The compile context A compile context is required if you want to change the default values of any of the following compile-time parameters: 

    -  What \R matches (Unicode newlines or CR, LF, CRLF only);
-  PCRE2's character tables;
-  The newline character sequence;
-  The compile time nested parentheses limit;
-  An external function for stack checking.
+  What \R matches (Unicode newlines or CR, LF, CRLF only)
+  PCRE2's character tables
+  The newline character sequence
+  The compile time nested parentheses limit
+  An external function for stack checking
    A compile context is also required if you are using custom memory management. If none of these apply, just pass NULL as the context argument of @@ -604,9 +602,8 @@ PCRE2_ERROR_BADDATA if invalid data is detected.
    The value must be PCRE2_BSR_ANYCRLF, to specify that \R matches only CR, LF, or CRLF, or PCRE2_BSR_UNICODE, to specify that \R matches any Unicode line -ending sequence. The value of this parameter does not affect what is compiled; -it is just saved with the compiled pattern. The value is used by the JIT -compiler and by the two interpreted matching functions, pcre2_match() and +ending sequence. The value is used by the JIT compiler and by the two +interpreted matching functions, pcre2_match() and pcre2_dfa_match(). int pcre2_set_character_tables(pcre2_compile_context *ccontext, const unsigned char *tables); @@ -709,12 +706,12 @@ in the subject string. This limit is not relevant to pcre2_dfa_match(), which ignores it.

    -When pcre2_match() is called with a pattern that was successfully studied -with pcre2_jit_compile(), the way that the matching is executed is -entirely different. However, there is still the possibility of runaway matching -that goes on for a very long time, and so the match_limit value is also -used in this case (but in a different way) to limit how long the matching can -continue. +When pcre2_match() is called with a pattern that was successfully +processed by pcre2_jit_compile(), the way in which matching is executed +is entirely different. However, there is still the possibility of runaway +matching that goes on for a very long time, and so the match_limit value +is also used in this case (but in a different way) to limit how long the +matching can continue.

    The default value for the limit can be set when PCRE2 is built; the default @@ -770,15 +767,17 @@ stack. There is a discussion about PCRE2's stack usage in the pcre2stack documentation. See the pcre2build -documentation for details of how to build PCRE2. Using the heap for recursion -is a non-standard way of building PCRE2, for use in environments that have -limited stacks. Because of the greater use of memory management, -pcre2_match() runs more slowly. Functions that are different to the -general custom memory functions are provided so that special-purpose external -code can be used for this case, because the memory blocks are all the same -size. The blocks are retained by pcre2_match() until it is about to exit -so that they can be re-used when possible during the match. In the absence of -these functions, the normal custom memory management functions are used, if +documentation for details of how to build PCRE2. +

    +

    +Using the heap for recursion is a non-standard way of building PCRE2, for use +in environments that have limited stacks. Because of the greater use of memory +management, pcre2_match() runs more slowly. Functions that are different +to the general custom memory functions are provided so that special-purpose +external code can be used for this case, because the memory blocks are all the +same size. The blocks are retained by pcre2_match() until it is about to +exit so that they can be re-used when possible during the match. In the absence +of these functions, the normal custom memory management functions are used, if supplied, otherwise the system functions.


    CHECKING BUILD-TIME OPTIONS
    @@ -809,9 +808,10 @@ available: PCRE2_CONFIG_BSR The output is an integer whose value indicates what character sequences the \R -escape sequence matches by default. A value of 0 means that \R matches any -Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, -or CRLF. The default can be overridden when a pattern is compiled or matched. +escape sequence matches by default. A value of PCRE2_BSR_UNICODE means that \R +matches any Unicode line ending sequence; a value of PCRE2_BSR_ANYCRLF means +that \R matches only CR, LF, or CRLF. The default can be overridden when a +pattern is compiled. 
       PCRE2_CONFIG_JIT
    @@ -821,7 +821,7 @@ compiling is available; otherwise it is set to zero. PCRE2_CONFIG_JITTARGET The where argument should point to a buffer that is at least 48 code -units long. (The exact length needed can be found by calling +units long. (The exact length required can be found by calling pcre2_config() with where set to NULL.) The buffer is filled with a string that contains the name of the architecture for which the JIT compiler is configured, for example "x86 32bit (little endian + unaligned)". If JIT support @@ -855,11 +855,11 @@ Further details are given with pcre2_match() below. The output is an integer whose value specifies the default character sequence that is recognized as meaning "newline". The values are: 
    -  1  Carriage return (CR)
-  2  Linefeed (LF)
-  3  Carriage return, linefeed (CRLF)
-  4  Any Unicode line ending
-  5  Any of CR, LF, or CRLF
+  PCRE2_NEWLINE_CR       Carriage return (CR)
+  PCRE2_NEWLINE_LF       Linefeed (LF)
+  PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+  PCRE2_NEWLINE_ANY      Any Unicode line ending
+  PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
    The default should normally correspond to the standard sequence for your operating system. @@ -891,7 +891,7 @@ heap instead of recursive function calls. PCRE2_CONFIG_UNICODE_VERSION The where argument should point to a buffer that is at least 24 code -units long. (The exact length needed can be found by calling +units long. (The exact length required can be found by calling pcre2_config() with where set to NULL.) If PCRE2 has been compiled without Unicode support, the buffer is filled with the text "Unicode not supported". Otherwise, the Unicode version string (for example, "7.0.0") is @@ -906,7 +906,7 @@ otherwise it is set to zero. Unicode support implies UTF support. PCRE2_CONFIG_VERSION The where argument should point to a buffer that is at least 12 code -units long. (The exact length needed can be found by calling +units long. (The exact length required can be found by calling pcre2_config() with where set to NULL.) The buffer is filled with the PCRE2 version string, zero-terminated. The number of code units used is returned. This is the length of the string plus one unit for the terminating @@ -922,17 +922,17 @@ zero. pcre2_code_free(pcre2_code *code);

    -This function compiles a pattern, defined by a pointer to a string of code -units and a length, into an internal form. If the pattern is zero-terminated, -the length should be specified as PCRE2_ZERO_TERMINATED. The function returns a -pointer to a block of memory that contains the compiled pattern and related -data. The caller must free the memory by calling pcre2_code_free() when -it is no longer needed. +The pcre2_compile() function compiles a pattern into an internal form. +The pattern is defined by a pointer to a string of code units and a length, If +the pattern is zero-terminated, the length can be specified as +PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of memory that +contains the compiled pattern and related data. The caller must free the memory +by calling pcre2_code_free() when it is no longer needed.

    -If the compile context argument ccontext is NULL, the memory is obtained -by calling malloc(). Otherwise, it is obtained from the same memory -function that was used for the compile context. +If the compile context argument ccontext is NULL, memory for the compiled +pattern is obtained by calling malloc(). Otherwise, it is obtained from +the same memory function that was used for the compile context.

    The options argument contains various bit settings that affect the @@ -1247,7 +1247,7 @@ classify characters. More details are given in the section on in the pcre2pattern page. If you set PCRE2_UCP, matching one of the items it affects takes much -longer. The option is available only if PCRE2 has been compiled with UTF +longer. The option is available only if PCRE2 has been compiled with Unicode support. 

       PCRE2_UNGREEDY
@@ -1260,9 +1260,10 @@ with Perl. It can also be set by a (?U) option setting within the pattern.
    This option causes PCRE2 to regard both the pattern and the subject strings that are subsequently processed as strings of UTF characters instead of -single-code-unit strings. However, it is available only when PCRE2 is built to -include UTF support. If not, the use of this option provokes an error. Details -of how this option changes the behaviour of PCRE2 are given in the +single-code-unit strings. It is available when PCRE2 is built to include +Unicode support (which is the default). If Unicode support is not available, +the use of this option provokes an error. Details of how this option changes +the behaviour of PCRE2 are given in the pcre2unicode page.

    @@ -1318,13 +1319,12 @@ Most, but not all patterns can be optimized by the JIT compiler.

    PCRE2 handles caseless matching, and determines whether characters are letters, digits, or whatever, by reference to a set of tables, indexed by character code -point. When running in UTF-8 mode, or using the 16-bit or 32-bit libraries, -this applies only to characters with code points less than 256. By default, -higher-valued code points never match escapes such as \w or \d. However, if -PCRE2 is built with UTF support, all characters can be tested with \p and \P, -or, alternatively, the PCRE2_UCP option can be set when a pattern is compiled; -this causes \w and friends to use Unicode property support instead of the -built-in tables. +point. This applies only to characters whose code points are less than 256. By +default, higher-valued code points never match escapes such as \w or \d. +However, if PCRE2 is built with UTF support, all characters can be tested with +\p and \P, or, alternatively, the PCRE2_UCP option can be set when a pattern +is compiled; this causes \w and friends to use Unicode property support +instead of the built-in tables.

    The use of locales with Unicode is discouraged. If you are handling characters @@ -1437,9 +1437,9 @@ are no back references. PCRE2_INFO_BSR The output is a uint32_t whose value indicates what character sequences the \R -escape sequence matches by default. A value of 0 means that \R matches any -Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, -or CRLF. The default can be overridden when a pattern is matched. +escape sequence matches. A value of PCRE2_BSR_UNICODE means that \R matches +any Unicode line ending sequence; a value of PCRE2_BSR_ANYCRLF means that \R +matches only CR, LF, or CRLF. 

       PCRE2_INFO_CAPTURECOUNT
    @@ -1581,15 +1581,18 @@ values.

    The map consists of a number of fixed-size entries. PCRE2_INFO_NAMECOUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives the size of each -entry; both of these return a uint32_t value. The entry size depends on -the length of the longest name. PCRE2_INFO_NAMETABLE returns a pointer to the -first entry of the table. This is a PCRE2_SPTR pointer to a block of code -units. In the 8-bit library, the first two bytes of each entry are the number -of the capturing parenthesis, most significant byte first. In the 16-bit -library, the pointer points to 16-bit data units, the first of which contains -the parenthesis number. In the 32-bit library, the pointer points to 32-bit -data units, the first of which contains the parenthesis number. The rest of the -entry is the corresponding name, zero terminated. +entry in code units; both of these return a uint32_t value. The entry +size depends on the length of the longest name. +

    +

    +PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table. This is +a PCRE2_SPTR pointer to a block of code units. In the 8-bit library, the first +two bytes of each entry are the number of the capturing parenthesis, most +significant byte first. In the 16-bit library, the pointer points to 16-bit +code units, the first of which contains the parenthesis number. In the 32-bit +library, the pointer points to 32-bit code units, the first of which contains +the parenthesis number. The rest of the entry is the corresponding name, zero +terminated.

    The names are in alphabetical order. If (?| is used to create multiple groups @@ -1629,17 +1632,16 @@ different for each compiled pattern. 

       PCRE2_INFO_NEWLINE
    -The output is a uint32_t whose value specifies the default character -sequence that will be recognized as meaning "newline" while matching. The -values are: +The output is a uint32_t with one of the following values: 
    -  1  Carriage return (CR)
-  2  Linefeed (LF)
-  3  Carriage return, linefeed (CRLF)
-  4  Any Unicode line ending
-  5  Any of CR, LF, or CRLF
+  PCRE2_NEWLINE_CR       Carriage return (CR)
+  PCRE2_NEWLINE_LF       Linefeed (LF)
+  PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+  PCRE2_NEWLINE_ANY      Any Unicode line ending
+  PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
    -The default can be overridden when a pattern is matched. +This specifies the default character sequence that will be recognized as +meaning "newline" while matching. 
       PCRE2_INFO_RECURSIONLIMIT
    @@ -1675,18 +1677,19 @@ Information about successful and unsuccessful matches is placed in a match data block, which is an opaque structure that is accessed by function calls. In particular, the match data block contains a vector of offsets into the subject string that define the matched part of the subject and any substrings that were -capured. This is know as the ovector. +captured. This is know as the ovector.

    -Before calling pcre2_match() or pcre2_dfa_match() you must create a -match data block by calling one of the creation functions above. For -pcre2_match_data_create(), the first argument is the number of pairs of -offsets in the ovector. One pair of offsets is required to identify the -string that matched the whole pattern, with another pair for each captured -substring. For example, a value of 4 creates enough space to record the matched -portion of the subject plus three captured substrings. A minimum of at least 1 -pair is imposed by pcre2_match_data_create(), so it is always possible to -return the overall matched string. +Before calling pcre2_match(), pcre2_dfa_match(), or +pcre2_jit_match() you must create a match data block by calling one of +the creation functions above. For pcre2_match_data_create(), the first +argument is the number of pairs of offsets in the ovector. One pair of +offsets is required to identify the string that matched the whole pattern, with +another pair for each captured substring. For example, a value of 4 creates +enough space to record the matched portion of the subject plus three captured +substrings. A minimum of at least 1 pair is imposed by +pcre2_match_data_create(), so it is always possible to return the overall +matched string.

    For pcre2_match_data_create_from_pattern(), the first argument is a @@ -1694,15 +1697,16 @@ pointer to a compiled pattern. In this case the ovector is created to be exactly the right size to hold all the substrings a pattern might capture.

    -The second argument of both these functions ia a pointer to a general context, +The second argument of both these functions is a pointer to a general context, which can specify custom memory management for obtaining the memory for the match data block. If you are not using custom memory management, pass NULL.

    A match data block can be used many times, with the same or different compiled patterns. When it is no longer needed, it should be freed by calling -pcre2_match_data_free(). How to extract information from a match data -block after a match operation is described in the sections on +pcre2_match_data_free(). You can extract information from a match data +block after a match operation has finished, using functions that are described +in the sections on matched strings and other match data @@ -1816,12 +1820,10 @@ PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their action is described below.

    -If the pattern was successfully processed by the just-in-time (JIT) compiler, -the only supported options for matching using the JIT code are PCRE2_NOTBOL, -PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, -PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. If an unsupported option is used, -JIT matching is disabled and the normal interpretive code in -pcre2_match() is run. +Setting PCRE2_ANCHORED at match time is not supported by the just-in-time (JIT) +compiler. If it is set, JIT matching is disabled and the normal interpretive +code in pcre2_match() is run. The remaining options are supported for JIT +matching. 

       PCRE2_ANCHORED
    @@ -1835,17 +1837,18 @@ matching. This option specifies that first character of the subject string is not the beginning of a line, so the circumflex metacharacter should not match before -it. Setting this without PCRE2_MULTILINE (at compile time) causes circumflex -never to match. This option affects only the behaviour of the circumflex -metacharacter. It does not affect \A. +it. Setting this without having set PCRE2_MULTILINE at compile time causes +circumflex never to match. This option affects only the behaviour of the +circumflex metacharacter. It does not affect \A. 
       PCRE2_NOTEOL
    This option specifies that the end of the subject string is not the end of a line, so the dollar metacharacter should not match it nor (except in multiline -mode) a newline immediately before it. Setting this without PCRE2_MULTILINE (at -compile time) causes dollar never to match. This option affects only the -behaviour of the dollar metacharacter. It does not affect \Z or \z. +mode) a newline immediately before it. Setting this without having set +PCRE2_MULTILINE at compile time causes dollar never to match. This option +affects only the behaviour of the dollar metacharacter. It does not affect \Z +or \z. 
       PCRE2_NOTEMPTY
    @@ -1857,13 +1860,16 @@ match the empty string, the entire match fails. For example, if the pattern is applied to a string not beginning with "a" or "b", it matches an empty string at the start of the subject. With PCRE2_NOTEMPTY set, this match is not -valid, so PCRE2 searches further into the string for occurrences of "a" or "b". +valid, so pcre2_match() searches further into the string for occurrences +of "a" or "b". 
       PCRE2_NOTEMPTY_ATSTART
    -This is like PCRE2_NOTEMPTY, except that an empty string match that is not at -the start of the subject is permitted. If the pattern is anchored, such a match -can occur only if the pattern contains \K. +This is like PCRE2_NOTEMPTY, except that it locks out an empty string match +only at the first matching position, that is, at the start of the subject plus +the starting offset. An empty string match later in the subject is permitted. +If the pattern is anchored, such a match can occur only if the pattern contains +\K. 
       PCRE2_NO_UTF_CHECK
    @@ -1904,8 +1910,8 @@ subject characters to complete the match. If this happens when PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, matching continues by testing any remaining alternatives. Only if no complete match can be found is PCRE2_ERROR_PARTIAL returned instead of PCRE2_ERROR_NOMATCH. In other words, -PCRE2_PARTIAL_SOFT says that the caller is prepared to handle a partial match, -but only if no complete match can be found. +PCRE2_PARTIAL_SOFT specifies that the caller is prepared to handle a partial +match, but only if no complete match can be found.

    If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this case, if @@ -1928,14 +1934,14 @@ a compile context. During matching, the newline choice affects the behaviour of the dot, circumflex, and dollar metacharacters. It may also alter the way the match -position is advanced after a match failure for an unanchored pattern. +starting position is advanced after a match failure for an unanchored pattern.

    -When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is set, -and a match attempt for an unanchored pattern fails when the current position -is at a CRLF sequence, and the pattern contains no explicit matches for CR or -LF characters, the match position is advanced by two characters instead of one, -in other words, to after the CRLF. +When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is set as +the newline convention, and a match attempt for an unanchored pattern fails +when the current starting position is at a CRLF sequence, and the pattern +contains no explicit matches for CR or LF characters, the match position is +advanced by two characters instead of one, in other words, to after the CRLF.

    The above rule is a compromise that makes the most common cases work as @@ -1948,8 +1954,8 @@ reference, and so advances only by one character after the first failure.

    An explicit match for CR of LF is either a literal appearance of one of those characters in the pattern, or one of the \r or \n escape sequences. Implicit -matches such as [^X] do not count, nor does \s (which includes CR and LF in -the characters that it matches). +matches such as [^X] do not count, nor does \s, even though it includes CR and +LF in the characters that it matches.

    Notwithstanding the above, anomalous effects may still occur when CRLF is a @@ -1967,16 +1973,16 @@ In general, a pattern matches a certain portion of the subject, and in addition, further substrings from the subject may be picked out by parenthesized parts of the pattern. Following the usage in Jeffrey Friedl's book, this is called "capturing" in what follows, and the phrase "capturing -subpattern" is used for a fragment of a pattern that picks out a substring. -PCRE2 supports several other kinds of parenthesized subpattern that do not -cause substrings to be captured. The pcre2_pattern_info() function can be -used to find out how many capturing subpatterns there are in a compiled -pattern. +subpattern" or "capturing group" is used for a fragment of a pattern that picks +out a substring. PCRE2 supports several other kinds of parenthesized subpattern +that do not cause substrings to be captured. The pcre2_pattern_info() +function can be used to find out how many capturing subpatterns there are in a +compiled pattern.

    The overall matched string and any captured substrings are returned to the -caller via a vector of PCRE2_SIZE values, called the ovector. This is -contained within the +caller via a vector of PCRE2_SIZE values. This is called the ovector, and +is contained within the match data block. You can obtain direct access to the ovector by calling pcre2_get_ovector_pointer() to find its address, and @@ -2045,9 +2051,7 @@ parentheses, no more than ovector[0] to ovector[2n+1] are set by pcre2_match(). The other elements retain whatever values they previously had.

    -
    -Other information about the match -
    +
    OTHER INFORMATION ABOUT A MATCH

    PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data);
    @@ -2055,7 +2059,7 @@ Other information about the match PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data);

    -In addition to the offsets in the ovector, other information about a match is +As well as the offsets in the ovector, other information about a match is retained in the match data block and can be retrieved by the above functions.

    @@ -2071,9 +2075,7 @@ different to the value of ovector[0] if the pattern contains the \K escape sequence. After a partial match, however, this value is always the same as ovector[0] because \K does not affect the result of a partial match.

    -
    -Error return values from pcre2_match() -
    +
    ERROR RETURNS FROM pcre2_match()

    If pcre2_match() fails, it returns a negative number. This can be converted to a text string by calling pcre2_get_error_message(). Negative @@ -2108,7 +2110,7 @@ passed to a 16-bit or 32-bit library function, or vice versa. 

       PCRE2_ERROR_BADOFFSET
    -The value of startoffset greater than the length of the subject. +The value of startoffset was greater than the length of the subject. 
       PCRE2_ERROR_BADOPTION
    @@ -2175,14 +2177,14 @@ the pattern. Specifically, it means that either the whole pattern or a subpattern has been called recursively for the second time at the same position in the subject string. Some simple patterns that might do this are detected and faulted at compile time, but more complicated cases, in particular mutual -recursions between two different subpatterns, cannot be detected until run -time. +recursions between two different subpatterns, cannot be detected until matching +is attempted. 
       PCRE2_ERROR_RECURSIONLIMIT
    The internal recursion limit was reached.

    -
    EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
    +
    EXTRACTING CAPTURED SUBSTRINGS BY NUMBER

    int pcre2_substring_length_bynumber(pcre2_match_data *match_data, unsigned int number, PCRE2_SIZE *length); @@ -2228,8 +2230,8 @@ extract the captured substrings.

    The final arguments of pcre2_substring_copy_bynumber() are a pointer to the buffer and a pointer to a variable that contains its length in code units. -This is updated to contain the actual number of code units used, excluding the -terminating zero. +This is updated to contain the actual number of code units used for the +extracted substring, excluding the terminating zero.

    For pcre2_substring_get_bynumber() the third and fourth arguments point @@ -2254,7 +2256,7 @@ no capturing group of that number in the pattern, or because the group with that number did not participate in the match, or because the ovector was too small to capture that group.

    -
    EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
    +
    EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS

    int pcre2_substring_list_get(pcre2_match_data *match_data, " PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr); @@ -2264,10 +2266,11 @@ small to capture that group.

    The pcre2_substring_list_get() function extracts all available substrings -and builds a list of pointers to them, and a second list that contains their -lengths (in code units), excluding a terminating zero that is added to each of -them. All this is done in a single block of memory that is obtained using the -same memory allocation function that was used to get the match data block. +and builds a list of pointers to them. It also (optionally) builds a second +list that contains their lengths (in code units), excluding a terminating zero +that is added to each of them. All this is done in a single block of memory +that is obtained using the same memory allocation function that was used to get +the match data block.

    The address of the memory block is returned via listptr, which is also @@ -2285,10 +2288,10 @@ If this function encounters a substring that is unset, which can happen when capturing subpattern number n+1 matches some part of the subject, but subpattern n has not been used at all, it returns an empty string. This can be distinguished from a genuine zero-length substring by inspecting the -appropriate offset in the ovector, which contains PCRE2_UNSET for unset +appropriate offset in the ovector, which contain PCRE2_UNSET for unset substrings.

    -
    EXTRACTING CAPTURED SUBSTRINGS BY NAME
    +
    EXTRACTING CAPTURED SUBSTRINGS BY NAME

    int pcre2_substring_number_from_name(const pcre2_code *code, PCRE2_SPTR name); @@ -2324,11 +2327,10 @@ that name.

    Given the number, you can extract the substring directly, or use one of the -functions described in the previous section. For convenience, there are also -"byname" functions that correspond to the "bynumber" functions, the only -difference being that the second argument is a name instead of a number. -However, if PCRE2_DUPNAMES is set and there are duplicate names, -the behaviour may not be what you want (see the next section). +functions described above. For convenience, there are also "byname" functions +that correspond to the "bynumber" functions, the only difference being that the +second argument is a name instead of a number. However, if PCRE2_DUPNAMES is +set and there are duplicate names, the behaviour may not be what you want.

    Warning: If the pattern uses the (?| feature to set up multiple @@ -2341,7 +2343,7 @@ names are not included in the compiled code. The matching process uses only numbers. For this reason, the use of different names for subpatterns of the same number causes an error at compile time.

    -
    CREATING A NEW STRING WITH SUBSTITUTIONS
    +
    CREATING A NEW STRING WITH SUBSTITUTIONS

    int pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length, PCRE2_SIZE startoffset, @@ -2368,8 +2370,8 @@ recognized: Either a group number or a group name can be given for <n>. Curly brackets are required only if the following character would be interpreted as part of the number or name. The number may be zero to include the entire matched string. -For example, if the pattern a(b)c is matched with "[abc]" and the replacement -string "+$1$0$1+", the result is "[+babcb+]". Group insertion is done by +For example, if the pattern a(b)c is matched with "=abc=" and the replacement +string "+$1$0$1+", the result is "=+babcb+=". Group insertion is done by calling pcre2_copy_byname() or pcre2_copy_bynumber() as appropriate.

    @@ -2402,7 +2404,7 @@ straight back. PCRE2_ERROR_BADREPLACEMENT is returned for an invalid replacement string (unrecognized sequence following a dollar sign), and PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough.

    -
    DUPLICATE SUBPATTERN NAMES
    +
    DUPLICATE SUBPATTERN NAMES

    int pcre2_substring_nametable_scan(const pcre2_code *code, PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); @@ -2423,19 +2425,21 @@ documentation. When duplicates are present, pcre2_substring_copy_byname() and pcre2_substring_get_byname() return the first substring corresponding to the given name that is set. If none are set, PCRE2_ERROR_NOSUBSTRING is -returned. The pcre2_substring_number_from_name() function returns one of -the numbers that are associated with the name, but it is not defined which it -is. +returned. The pcre2_substring_number_from_name() function returns +the error PCRE2_ERROR_NOUNIQUESUBSTRING.

    If you want to get full details of all captured substrings for a given name, you must use the pcre2_substring_nametable_scan() function. The first argument is the compiled pattern, and the second is the name. If the third and -fourth arguments are NULL, the function returns a group number (it is not -defined which). Otherwise, the third and fourth arguments must be pointers to +fourth arguments are NULL, the function returns a group number for a unique +name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise. +

    +

    +When the third and fourth arguments are not NULL, they must be pointers to variables that are updated by the function. After it has run, they point to the first and last entries in the name-to-number table for the given name, and the -function returns the length of each entry. In both cases, +function returns the length of each entry in code units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name.

    @@ -2445,14 +2449,14 @@ The format of the name table is described above in the section entitled Given all the relevant entries for the name, you can extract each of their numbers, and hence the captured data.

    -
    FINDING ALL POSSIBLE MATCHES
    +
    FINDING ALL POSSIBLE MATCHES AT ONE POSITION

    The traditional matching function uses a similar algorithm to Perl, which stops -when it finds the first match, starting at a given point in the subject. If you -want to find all possible matches, or the longest possible match at a given -position, consider using the alternative matching function (see below) instead. -If you cannot use the alternative function, you can kludge it up by making use -of the callout facility, which is described in the +when it finds the first match at a given point in the subject. If you want to +find all possible matches, or the longest possible match at a given position, +consider using the alternative matching function (see below) instead. If you +cannot use the alternative function, you can kludge it up by making use of the +callout facility, which is described in the pcre2callout documentation.

    @@ -2463,7 +2467,7 @@ substring. Then return 1, which forces pcre2_match() to backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH.

    -
    MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
    +
    MATCHING A PATTERN: THE ALTERNATIVE FUNCTION

    int pcre2_dfa_match(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length, PCRE2_SIZE startoffset, @@ -2591,11 +2595,10 @@ the longest matches.

    NOTE: PCRE2's "auto-possessification" optimization usually applies to character repeats at the end of a pattern (as well as internally). For example, the -pattern "a\d+" is compiled as if it were "a\d++" because there is no point in -backtracking into the repeated digits. For DFA matching, this means that only -one possible match is found. If you really do want multiple matches in such -cases, either use an ungreedy repeat ("a\d+?") or set the -PCRE2_NO_AUTO_POSSESS option when compiling. +pattern "a\d+" is compiled as if it were "a\d++". For DFA matching, this +means that only one possible match is found. If you really do want multiple +matches in such cases, either use an ungreedy repeat auch as "a\d+?" or set +the PCRE2_NO_AUTO_POSSESS option when compiling.


    Error returns from pcre2_dfa_match() @@ -2633,29 +2636,29 @@ extremely rare, as a vector of size 1000 is used. 
       PCRE2_ERROR_DFA_BADRESTART
    -When pcre2_dfa_match() is called with the pcre2_dfa_RESTART option, +When pcre2_dfa_match() is called with the PCRE2_DFA_RESTART option, some plausibility checks are made on the contents of the workspace, which should contain data about the previous partial match. If any of these checks fail, this error is given.

    -
    SEE ALSO
    +
    SEE ALSO

    -pcre2build(3), pcre2libs(3), pcre2callout(3), +pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), pcre2partial(3), pcre2posix(3), -pcre2demo(3), pcre2sample(3), pcre2stack(3). +pcre2sample(3), pcre2stack(3), pcre2unicode(3).

    -
    AUTHOR
    +
    AUTHOR

    Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.

    -
    REVISION
    +
    REVISION

    -Last updated: 11 November 2014 +Last updated: 21 November 2014
    Copyright © 1997-2014 University of Cambridge.
    diff --git a/doc/html/pcre2build.html b/doc/html/pcre2build.html index 6b5b8e2..c6ba6de 100644 --- a/doc/html/pcre2build.html +++ b/doc/html/pcre2build.html @@ -461,7 +461,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    REVISION
    diff --git a/doc/html/pcre2callout.html b/doc/html/pcre2callout.html index 6d2c3c6..baf76e1 100644 --- a/doc/html/pcre2callout.html +++ b/doc/html/pcre2callout.html @@ -256,7 +256,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    REVISION
    diff --git a/doc/html/pcre2compat.html b/doc/html/pcre2compat.html index 8435434..2939a88 100644 --- a/doc/html/pcre2compat.html +++ b/doc/html/pcre2compat.html @@ -207,7 +207,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    diff --git a/doc/html/pcre2grep.html b/doc/html/pcre2grep.html index 6528a38..0a5b5cb 100644 --- a/doc/html/pcre2grep.html +++ b/doc/html/pcre2grep.html @@ -745,7 +745,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    REVISION
    diff --git a/doc/html/pcre2jit.html b/doc/html/pcre2jit.html index b1d0609..3e3092e 100644 --- a/doc/html/pcre2jit.html +++ b/doc/html/pcre2jit.html @@ -413,7 +413,7 @@ Philip Hazel (FAQ by Zoltan Herczeg)
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    REVISION
    diff --git a/doc/html/pcre2limits.html b/doc/html/pcre2limits.html index 4de3cf1..29aca8c 100644 --- a/doc/html/pcre2limits.html +++ b/doc/html/pcre2limits.html @@ -73,7 +73,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    diff --git a/doc/html/pcre2matching.html b/doc/html/pcre2matching.html index eab6179..859bbb3 100644 --- a/doc/html/pcre2matching.html +++ b/doc/html/pcre2matching.html @@ -227,7 +227,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    REVISION
    diff --git a/doc/html/pcre2partial.html b/doc/html/pcre2partial.html index 50edcfd..00bfe5d 100644 --- a/doc/html/pcre2partial.html +++ b/doc/html/pcre2partial.html @@ -450,7 +450,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    REVISION
    diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index e7073a2..3237c8f 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -3231,7 +3231,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    REVISION
    diff --git a/doc/html/pcre2perform.html b/doc/html/pcre2perform.html index 0e182e7..1b0b145 100644 --- a/doc/html/pcre2perform.html +++ b/doc/html/pcre2perform.html @@ -180,7 +180,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    diff --git a/doc/html/pcre2posix.html b/doc/html/pcre2posix.html index 93829b3..5e4b5a3 100644 --- a/doc/html/pcre2posix.html +++ b/doc/html/pcre2posix.html @@ -278,7 +278,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    REVISION
    diff --git a/doc/html/pcre2sample.html b/doc/html/pcre2sample.html index 1cba300..60a928b 100644 --- a/doc/html/pcre2sample.html +++ b/doc/html/pcre2sample.html @@ -90,7 +90,7 @@ Philip Hazel
    University Computing Service
    -Cambridge CB2 3QH, England. +Cambridge, England.


    diff --git a/doc/html/pcre2stack.html b/doc/html/pcre2stack.html index 978f241..2942c7a 100644 --- a/doc/html/pcre2stack.html +++ b/doc/html/pcre2stack.html @@ -33,6 +33,13 @@ the recursive call would immediately be passed back as the result of the current call (a "tail recursion"), the function is just restarted instead.

    +Each time the internal match() function is called recursively, it uses +memory from the process stack. For certain kinds of pattern and data, very +large amounts of stack may be needed, despite the recognition of "tail +recursion". Note that if PCRE2 is compiled with the -fsanitize=address option +of the GCC compiler, the stack requirements are greatly increased. +

    +

    The above comments apply when pcre2_match() is run in its normal interpretive manner. If the compiled pattern was processed by pcre2_jit_compile(), and just-in-time compiling was successful, and the @@ -61,10 +68,7 @@ relevant only for pcre2_match() without the JIT optimization. Reducing pcre2_match()'s stack usage

    -Each time that the internal match() function is called recursively, it -uses memory from the process stack. For certain kinds of pattern and data, very -large amounts of stack may be needed, despite the recognition of "tail -recursion". You can often reduce the amount of recursion, and therefore the +You can often reduce the amount of recursion, and therefore the amount of stack used, by modifying the pattern that is being matched. Consider, for example, this pattern: 

    @@ -187,14 +191,14 @@ Philip Hazel
 
    
 University Computing Service
 
    
-Cambridge CB2 3QH, England.
+Cambridge, England.
 
    
 
    
 
    
 REVISION
 
    
 
    
-Last updated: 20 October 2014
+Last updated: 21 November 2014
 
    
 Copyright © 1997-2014 University of Cambridge.
 
    
diff --git a/doc/html/pcre2syntax.html b/doc/html/pcre2syntax.html
index 698ce36..7937059 100644
--- a/doc/html/pcre2syntax.html
+++ b/doc/html/pcre2syntax.html
@@ -548,7 +548,7 @@ Philip Hazel
 
    
 University Computing Service
 
    
-Cambridge CB2 3QH, England.
+Cambridge, England.
 
    
 
    
 
    REVISION
    
diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html
index fb6656f..2dc6040 100644
--- a/doc/html/pcre2test.html
+++ b/doc/html/pcre2test.html
@@ -1301,7 +1301,7 @@ Philip Hazel
 
    
 University Computing Service
 
    
-Cambridge CB2 3QH, England.
+Cambridge, England.
 
    
 
    
 
    REVISION
    
diff --git a/doc/html/pcre2unicode.html b/doc/html/pcre2unicode.html
index bc3b327..4e8c4ea 100644
--- a/doc/html/pcre2unicode.html
+++ b/doc/html/pcre2unicode.html
@@ -254,7 +254,7 @@ Philip Hazel
 
    
 University Computing Service
 
    
-Cambridge CB2 3QH, England.
+Cambridge, England.
 
    
 
    
 
    
diff --git a/doc/pcre2.3 b/doc/pcre2.3
index 5415800..dd4e53c 100644
--- a/doc/pcre2.3
+++ b/doc/pcre2.3
@@ -146,7 +146,7 @@ listing), and the short pages for individual functions, are concatenated in
   pcre2matching      discussion of the two matching algorithms
   pcre2partial       details of the partial matching facility
 .\" JOIN
-  pcre2pattern       syntax and semantics of supported regular 
+  pcre2pattern       syntax and semantics of supported regular
                        expression patterns
   pcre2perform       discussion of performance issues
   pcre2posix         the POSIX-compatible C API for the 8-bit library
diff --git a/doc/pcre2.txt b/doc/pcre2.txt
index 4dd9ae6..71cfe4e 100644
--- a/doc/pcre2.txt
+++ b/doc/pcre2.txt
@@ -22,9 +22,9 @@ INTRODUCTION
        pattern matching using the same syntax and semantics as Perl, with just
        a few differences. Some features that appeared in Python and the origi-
        nal  PCRE  before  they  appeared  in Perl are also available using the
-       Python syntax, there is some support for one or two .NET and  Oniguruma
-       syntax  items,  and there are options for requesting some minor changes
-       that give better ECMAScript (aka JavaScript) compatibility.
+       Python syntax. There is also some support for one or two .NET and Onig-
+       uruma  syntax  items,  and  there are options for requesting some minor
+       changes that give better ECMAScript (aka JavaScript) compatibility.
 
        The source code for PCRE2 can be compiled to support 8-bit, 16-bit,  or
        32-bit  code units, which means that up to three separate libraries may
@@ -33,7 +33,7 @@ INTRODUCTION
        tively. In all three cases, strings can be interpreted  either  as  one
        character  per  code  unit, or as UTF-encoded Unicode, with support for
        Unicode general category properties. Unicode  support  is  optional  at
-       build  time  (but  is  the default); however, processing strings as UTF
+       build  time  (but  is  the default). However, processing strings as UTF
        code units must be enabled explicitly at run time. The version of  Uni-
        code in use can be discovered by running
 
@@ -124,22 +124,21 @@ USER DOCUMENTATION
          pcre2compat        discussion of Perl compatibility
          pcre2demo          a demonstration C program that uses PCRE2
          pcre2grep          description of the pcre2grep command (8-bit only)
-         pcre2jit           discussion of the just-in-time  optimization  sup-
-       port
+         pcre2jit           discussion of just-in-time optimization support
          pcre2limits        details of size and other limits
          pcre2matching      discussion of the two matching algorithms
          pcre2partial       details of the partial matching facility
-         pcre2pattern       syntax and semantics of supported
-                             regular expressions
+         pcre2pattern       syntax and semantics of supported regular
+                              expression patterns
          pcre2perform       discussion of performance issues
          pcre2posix         the POSIX-compatible C API for the 8-bit library
          pcre2sample        discussion of the pcre2demo program
          pcre2stack         discussion of stack usage
          pcre2syntax        quick syntax reference
-         pcre2test          description of the pcre2test testing command
+         pcre2test          description of the pcre2test command
          pcre2unicode       discussion of Unicode and UTF support
 
-       In  the  "man"  and HTML formats, there is also a short page for each C
+       In the "man" and HTML formats, there is also a short page  for  each  C
        library function, listing its arguments and results.
 
 
@@ -147,16 +146,16 @@ AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
-       Putting an actual email address here is a spam magnet. If you  want  to
-       email  me,  use  my two initials, followed by the two digits 10, at the
+       Putting  an  actual email address here is a spam magnet. If you want to
+       email me, use my two initials, followed by the two digits  10,  at  the
        domain cam.ac.uk.
 
 
 REVISION
 
-       Last updated: 03 November 2014
+       Last updated: 18 November 2014
        Copyright (c) 1997-2014 University of Cambridge.
 ------------------------------------------------------------------------------
 
@@ -506,100 +505,97 @@ NEWLINES
        Each  of  the first three conventions is used by at least one operating
        system as its standard newline sequence. When PCRE2 is built, a default
        can  be  specified.  The default default is LF, which is the Unix stan-
-       dard. When PCRE2 is run, the default can be overridden, either  when  a
-       pattern is compiled, or when it is matched.
+       dard. However, the newline convention can be changed by an  application
+       when calling pcre2_compile(), or it can be specified by special text at
+       the start of the pattern itself; this overrides any other settings. See
+       the pcre2pattern page for details of the special character sequences.
 
-       The  newline convention can be changed when calling pcre2_compile(), or
-       it can be specified by special text at the start of the pattern itself;
-       this  overrides  any  other  settings.  See  the  pcre2pattern page for
-       details of the special character sequences.
-
-       In the PCRE2 documentation the word "newline"  is  used  to  mean  "the
+       In  the  PCRE2  documentation  the  word "newline" is used to mean "the
        character or pair of characters that indicate a line break". The choice
-       of newline convention affects the handling of the dot, circumflex,  and
+       of  newline convention affects the handling of the dot, circumflex, and
        dollar metacharacters, the handling of #-comments in /x mode, and, when
-       CRLF is a recognized line ending sequence, the match position  advance-
+       CRLF  is a recognized line ending sequence, the match position advance-
        ment for a non-anchored pattern. There is more detail about this in the
        section on pcre2_match() options below.
 
-       The choice of newline convention does not affect the interpretation  of
-       the  \n  or  \r  escape  sequences, nor does it affect what \R matches,
-       which has its own separate control.
+       The  choice of newline convention does not affect the interpretation of
+       the \n or \r escape sequences, nor does it affect what \R matches; this
+       has its own separate convention.
 
 
 MULTITHREADING
 
-       In a multithreaded application it is important to keep  thread-specific
-       data  separate  from data that can be shared between threads. The PCRE2
-       library code itself is thread-safe: it contains  no  static  or  global
-       variables.  The  API  is  designed to be fairly simple for non-threaded
-       applications while at the same time ensuring that multithreaded  appli-
+       In  a multithreaded application it is important to keep thread-specific
+       data separate from data that can be shared between threads.  The  PCRE2
+       library  code  itself  is  thread-safe: it contains no static or global
+       variables. The API is designed to be  fairly  simple  for  non-threaded
+       applications  while at the same time ensuring that multithreaded appli-
        cations can use it.
 
        There are several different blocks of data that are used to pass infor-
-       mation between the application and the PCRE libraries.
+       mation between the application and the PCRE2 libraries.
 
        (1) A pointer to the compiled form of a pattern is returned to the user
        when pcre2_compile() is successful. The data in the compiled pattern is
-       fixed, and does not change when the pattern is matched.  Therefore,  it
-       is  thread-safe, that is, the same compiled pattern can be used by more
+       fixed,  and  does not change when the pattern is matched. Therefore, it
+       is thread-safe, that is, the same compiled pattern can be used by  more
        than one thread simultaneously. An application can compile all its pat-
-       terns  at the start, before forking off multiple threads that use them.
-       However, if the just-in-time optimization feature  is  being  used,  it
-       needs  separate  memory  stack  areas for each thread. See the pcre2jit
+       terns at the start, before forking off multiple threads that use  them.
+       However,  if  the  just-in-time  optimization feature is being used, it
+       needs separate memory stack areas for each  thread.  See  the  pcre2jit
        documentation for more details.
 
-       (2) The next section below introduces the idea of "contexts"  in  which
+       (2)  The  next section below introduces the idea of "contexts" in which
        PCRE2 functions are called. A context is nothing more than a collection
        of parameters that control the way PCRE2 operates. Grouping a number of
        parameters together in a context is a convenient way of passing them to
-       a PCRE2 function without using lots of arguments. The  parameters  that
-       are  stored  in  contexts  are in some sense "advanced features" of the
+       a  PCRE2  function without using lots of arguments. The parameters that
+       are stored in contexts are in some sense  "advanced  features"  of  the
        API. Many straightforward applications will not need to use contexts.
 
        In a multithreaded application, if the parameters in a context are val-
-       ues  that  are  never  changed, the same context can be used by all the
+       ues that are never changed, the same context can be  used  by  all  the
        threads. However, if any thread needs to change any value in a context,
        it must make its own thread-specific copy.
 
        (3) The matching functions need a block of memory for working space and
-       for storing the results of a match. This includes details of  what  was
-       matched,  as  well  as  additional  information  such  as the name of a
-       (*MARK) setting. Each thread must provide its own version of this  mem-
+       for  storing  the results of a match. This includes details of what was
+       matched, as well as additional  information  such  as  the  name  of  a
+       (*MARK)  setting. Each thread must provide its own version of this mem-
        ory.
 
 
 PCRE2 CONTEXTS
 
-       Some  PCRE2  functions have a lot of parameters, many of which are used
-       only by specialist applications, for example,  those  that  use  custom
-       memory  management  or  non-standard character tables. To keep function
-       argument lists at a reasonable size, and at the same time to  keep  the
-       API  extensible,  "uncommon" parameters are passed to certain functions
-       in a context instead of directly. A context is just a block  of  memory
-       that  holds  the  parameter  values.   Applications that do not need to
-       adjust any of the context parameters  can  pass  NULL  when  a  context
+       Some PCRE2 functions have a lot of parameters, many of which  are  used
+       only  by  specialist  applications,  for example, those that use custom
+       memory management or non-standard character tables.  To  keep  function
+       argument  lists  at a reasonable size, and at the same time to keep the
+       API extensible, "uncommon" parameters are passed to  certain  functions
+       in  a  context instead of directly. A context is just a block of memory
+       that holds the parameter values.  Applications  that  do  not  need  to
+       adjust  any  of  the  context  parameters  can pass NULL when a context
        pointer is required.
 
-       There  are  three different types of context: a general context that is
-       relevant for several PCRE2 operations, a compile-time  context,  and  a
+       There are three different types of context: a general context  that  is
+       relevant  for  several  PCRE2 operations, a compile-time context, and a
        match-time context.
 
    The general context
 
-       At  present,  this  context  just  contains  pointers to (and data for)
-       external memory management  functions  that  are  called  from  several
+       At present, this context just  contains  pointers  to  (and  data  for)
+       external  memory  management  functions  that  are  called from several
        places in the PCRE2 library. The context is named `general' rather than
-       specifically `memory' because in future other fields may be  added.  If
-       you  do not want to supply your own custom memory management functions,
-       you do not need to bother with a general context. A general context  is
+       specifically  `memory'  because in future other fields may be added. If
+       you do not want to supply your own custom memory management  functions,
+       you  do not need to bother with a general context. A general context is
        created by:
 
        pcre2_general_context *pcre2_general_context_create(
          void *(*private_malloc)(PCRE2_SIZE, void *),
          void (*private_free)(void *, void *), void *memory_data);
 
-       The  two  function pointers specify custom memory management functions,
+       The two function pointers specify custom memory  management  functions,
        whose prototypes are:
 
          void *private_malloc(PCRE2_SIZE, void *);
@@ -607,16 +603,16 @@ PCRE2 CONTEXTS
 
        Whenever code in PCRE2 calls these functions, the final argument is the
        value of memory_data. Either of the first two arguments of the creation
-       function may be NULL, in which case the system memory management  func-
-       tions  malloc()  and free() are used. (This is not currently useful, as
-       there are no other fields in a general context,  but  in  future  there
-       might  be.)   The  private_malloc()  function  is used (if supplied) to
-       obtain memory for storing the context, and all three values  are  saved
+       function  may be NULL, in which case the system memory management func-
+       tions malloc() and free() are used. (This is not currently  useful,  as
+       there  are  no  other  fields in a general context, but in future there
+       might be.)  The private_malloc() function  is  used  (if  supplied)  to
+       obtain  memory  for storing the context, and all three values are saved
        as part of the context.
 
-       Whenever  PCRE2  creates a data block of any kind, the block contains a
-       pointer to the free() function that matches the malloc() function  that
-       was  used.  When  the  time  comes  to free the block, this function is
+       Whenever PCRE2 creates a data block of any kind, the block  contains  a
+       pointer  to the free() function that matches the malloc() function that
+       was used. When the time comes to  free  the  block,  this  function  is
        called.
 
        A general context can be copied by calling:
@@ -631,20 +627,20 @@ PCRE2 CONTEXTS
 
    The compile context
 
-       A compile context is required if you want to change the default  values
+       A  compile context is required if you want to change the default values
        of any of the following compile-time parameters:
 
-         What \R matches (Unicode newlines or CR, LF, CRLF only);
-         PCRE2's character tables;
-         The newline character sequence;
-         The compile time nested parentheses limit;
-         An external function for stack checking.
+         What \R matches (Unicode newlines or CR, LF, CRLF only)
+         PCRE2's character tables
+         The newline character sequence
+         The compile time nested parentheses limit
+         An external function for stack checking
 
-       A  compile context is also required if you are using custom memory man-
-       agement.  If none of these apply, just pass NULL as the  context  argu-
+       A compile context is also required if you are using custom memory  man-
+       agement.   If  none of these apply, just pass NULL as the context argu-
        ment of pcre2_compile().
 
-       A  compile context is created, copied, and freed by the following func-
+       A compile context is created, copied, and freed by the following  func-
        tions:
 
        pcre2_compile_context *pcre2_compile_context_create(
@@ -655,19 +651,18 @@ PCRE2 CONTEXTS
 
        void pcre2_compile_context_free(pcre2_compile_context *ccontext);
 
-       A compile context is created with default values  for  its  parameters.
+       A  compile  context  is created with default values for its parameters.
        These can be changed by calling the following functions, which return 0
        on success, or PCRE2_ERROR_BADDATA if invalid data is detected.
 
        int pcre2_set_bsr(pcre2_compile_context *ccontext,
          uint32_t value);
 
-       The value must be PCRE2_BSR_ANYCRLF, to specify that  \R  matches  only
-       CR,  LF,  or CRLF, or PCRE2_BSR_UNICODE, to specify that \R matches any
-       Unicode line ending sequence. The value  of  this  parameter  does  not
-       affect  what  is  compiled; it is just saved with the compiled pattern.
-       The value is used by the JIT compiler and by the two interpreted match-
-       ing functions, pcre2_match() and pcre2_dfa_match().
+       The  value  must  be PCRE2_BSR_ANYCRLF, to specify that \R matches only
+       CR, LF, or CRLF, or PCRE2_BSR_UNICODE, to specify that \R  matches  any
+       Unicode line ending sequence. The value is used by the JIT compiler and
+       by  the  two  interpreted   matching   functions,   pcre2_match()   and
+       pcre2_dfa_match().
 
        int pcre2_set_character_tables(pcre2_compile_context *ccontext,
          const unsigned char *tables);
@@ -763,8 +758,8 @@ PCRE2 CONTEXTS
        from  zero  for  each position in the subject string. This limit is not
        relevant to pcre2_dfa_match(), which ignores it.
 
-       When pcre2_match() is called with a pattern that was successfully stud-
-       ied  with pcre2_jit_compile(), the way that the matching is executed is
+       When pcre2_match() is called with a pattern that was successfully  pro-
+       cessed by pcre2_jit_compile(), the way in which matching is executed is
        entirely different. However, there is still the possibility of  runaway
        matching  that  goes  on  for  a very long time, and so the match_limit
        value is also used in this case (but in a different way) to  limit  how
@@ -819,49 +814,50 @@ PCRE2 CONTEXTS
        remembering backtracking data, instead of recursive function calls that
        use the system stack. There is a discussion about PCRE2's  stack  usage
        in  the  pcre2stack documentation. See the pcre2build documentation for
-       details of how to build PCRE2. Using the heap for recursion is  a  non-
-       standard  way of building PCRE2, for use in environments that have lim-
-       ited  stacks.  Because  of  the  greater  use  of  memory   management,
-       pcre2_match()  runs  more  slowly.  Functions that are different to the
-       general custom memory functions are provided  so  that  special-purpose
-       external  code can be used for this case, because the memory blocks are
-       all the same size. The blocks are retained by pcre2_match() until it is
-       about  to  exit  so  that  they can be re-used when possible during the
-       match. In the absence of these functions, the normal custom memory man-
-       agement  functions  are  used,  if supplied, otherwise the system func-
-       tions.
+       details of how to build PCRE2.
+
+       Using the heap for recursion is a non-standard way of  building  PCRE2,
+       for  use  in  environments  that  have  limited  stacks. Because of the
+       greater use of memory management, pcre2_match() runs more slowly. Func-
+       tions  that  are  different  to the general custom memory functions are
+       provided so that special-purpose external code can  be  used  for  this
+       case,  because  the memory blocks are all the same size. The blocks are
+       retained by pcre2_match() until it is about to exit so that they can be
+       re-used  when  possible during the match. In the absence of these func-
+       tions, the normal custom memory management functions are used, if  sup-
+       plied, otherwise the system functions.
 
 
 CHECKING BUILD-TIME OPTIONS
 
        int pcre2_config(uint32_t what, void *where);
 
-       The function pcre2_config() makes it possible for  a  PCRE2  client  to
-       discover  which  optional  features  have  been compiled into the PCRE2
-       library. The pcre2build documentation  has  more  details  about  these
+       The  function  pcre2_config()  makes  it possible for a PCRE2 client to
+       discover which optional features have  been  compiled  into  the  PCRE2
+       library.  The  pcre2build  documentation  has  more details about these
        optional features.
 
-       The  first  argument  for pcre2_config() specifies which information is
-       required. The second argument is a pointer to  memory  into  which  the
-       information  is  placed.  If  NULL  is passed, the function returns the
-       amount of memory that is needed  for  the  requested  information.  For
-       calls  that  return  numerical  values,  the  value  is  in bytes; when
-       requesting these values, where should point  to  appropriately  aligned
-       memory.  For calls that return strings, the required length is given in
+       The first argument for pcre2_config() specifies  which  information  is
+       required.  The  second  argument  is a pointer to memory into which the
+       information is placed. If NULL is  passed,  the  function  returns  the
+       amount  of  memory  that  is  needed for the requested information. For
+       calls that return  numerical  values,  the  value  is  in  bytes;  when
+       requesting  these  values,  where should point to appropriately aligned
+       memory. For calls that return strings, the required length is given  in
        code units, not counting the terminating zero.
 
-       When requesting information, the returned value from pcre2_config()  is
-       non-negative  on success, or the negative error code PCRE2_ERROR_BADOP-
-       TION if the value in the first argument is not recognized. The  follow-
+       When  requesting information, the returned value from pcre2_config() is
+       non-negative on success, or the negative error code  PCRE2_ERROR_BADOP-
+       TION  if the value in the first argument is not recognized. The follow-
        ing information is available:
 
          PCRE2_CONFIG_BSR
 
        The output is an integer whose value indicates what character sequences
-       the \R escape sequence matches by default. A value of 0 means  that  \R
-       matches  any  Unicode  line ending sequence; a value of 1 means that \R
-       matches only CR, LF, or CRLF. The default can be overridden when a pat-
-       tern is compiled or matched.
+       the \R escape sequence matches by default. A value of PCRE2_BSR_UNICODE
+       means that \R matches any Unicode line  ending  sequence;  a  value  of
+       PCRE2_BSR_ANYCRLF  means  that  \R  matches  only  CR, LF, or CRLF. The
+       default can be overridden when a pattern is compiled.
 
          PCRE2_CONFIG_JIT
 
@@ -870,98 +866,98 @@ CHECKING BUILD-TIME OPTIONS
 
          PCRE2_CONFIG_JITTARGET
 
-       The where argument should point to a buffer that is at  least  48  code
-       units long. (The exact length needed can be found by calling pcre2_con-
-       fig() with where set to NULL.) The buffer is filled with a string  that
-       contains  the  name  of  the architecture for which the JIT compiler is
-       configured, for example "x86 32bit (little endian + unaligned)". If JIT
-       support  is not available, PCRE2_ERROR_BADOPTION is returned, otherwise
-       the number of code units used is returned. This is the  length  of  the
-       string, plus one unit for the terminating zero.
+       The  where  argument  should point to a buffer that is at least 48 code
+       units long.  (The  exact  length  required  can  be  found  by  calling
+       pcre2_config()  with  where  set  to NULL.) The buffer is filled with a
+       string that contains the name of the architecture  for  which  the  JIT
+       compiler  is  configured,  for  example  "x86  32bit  (little  endian +
+       unaligned)". If JIT support is not available, PCRE2_ERROR_BADOPTION  is
+       returned,  otherwise the number of code units used is returned. This is
+       the length of the string, plus one unit for the terminating zero.
 
          PCRE2_CONFIG_LINKSIZE
 
-       The  output  is  an  integer that contains the number of bytes used for
+       The output is an integer that contains the number  of  bytes  used  for
        internal linkage in compiled regular expressions. When PCRE2 is config-
-       ured,  the  value  can  be set to 2, 3, or 4, with the default being 2.
+       ured, the value can be set to 2, 3, or 4, with  the  default  being  2.
        This is the value that is returned by pcre2_config(). However, when the
-       16-bit  library  is compiled, a value of 3 is rounded up to 4, and when
-       the 32-bit library is compiled, internal linkages always use  4  bytes,
+       16-bit library is compiled, a value of 3 is rounded up to 4,  and  when
+       the  32-bit  library is compiled, internal linkages always use 4 bytes,
        so the configured value is not relevant.
 
        The default value of 2 for the 8-bit and 16-bit libraries is sufficient
-       for all but the most massive patterns, since it allows the size of  the
+       for  all but the most massive patterns, since it allows the size of the
        compiled pattern to be up to 64K code units. Larger values allow larger
-       regular expressions to be compiled by those two libraries, but  at  the
+       regular  expressions  to be compiled by those two libraries, but at the
        expense of slower matching.
 
          PCRE2_CONFIG_MATCHLIMIT
 
        The output is an unsigned long integer that gives the default limit for
-       the number of internal matching function calls in a pcre2_match()  exe-
+       the  number of internal matching function calls in a pcre2_match() exe-
        cution.  Further details are given with pcre2_match() below.
 
          PCRE2_CONFIG_NEWLINE
 
-       The  output  is  an integer whose value specifies the default character
+       The output is an integer whose value specifies  the  default  character
        sequence that is recognized as meaning "newline". The values are:
 
-         1  Carriage return (CR)
-         2  Linefeed (LF)
-         3  Carriage return, linefeed (CRLF)
-         4  Any Unicode line ending
-         5  Any of CR, LF, or CRLF
+         PCRE2_NEWLINE_CR       Carriage return (CR)
+         PCRE2_NEWLINE_LF       Linefeed (LF)
+         PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+         PCRE2_NEWLINE_ANY      Any Unicode line ending
+         PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
 
-       The default should normally correspond to  the  standard  sequence  for
+       The  default  should  normally  correspond to the standard sequence for
        your operating system.
 
          PCRE2_CONFIG_PARENSLIMIT
 
-       The  output is an unsigned long integer that gives the maximum depth of
-       nesting of parentheses (of any  kind)  in  a  pattern.  This  limit  is
-       imposed  to  cap the amount of system stack used when a pattern is com-
-       piled. It is specified when PCRE2 is built; the default  is  250.  This
-       limit  does not take into account the stack that may already be used by
-       the calling application.  For  finer  control  over  compilation  stack
+       The output is an unsigned long integer that gives the maximum depth  of
+       nesting  of  parentheses  (of  any  kind)  in  a pattern. This limit is
+       imposed to cap the amount of system stack used when a pattern  is  com-
+       piled.  It  is  specified when PCRE2 is built; the default is 250. This
+       limit does not take into account the stack that may already be used  by
+       the  calling  application.  For  finer  control  over compilation stack
        usage, see pcre2_set_compile_recursion_guard().
 
          PCRE2_CONFIG_RECURSIONLIMIT
 
        The output is an unsigned long integer that gives the default limit for
        the depth of recursion when calling the internal matching function in a
-       pcre2_match()  execution.  Further details are given with pcre2_match()
+       pcre2_match() execution. Further details are given  with  pcre2_match()
        below.
 
          PCRE2_CONFIG_STACKRECURSE
 
-       The output is an integer that is set to one if internal recursion  when
-       running  pcre2_match()  is implemented by recursive function calls that
-       use the system stack to remember their state. This  is  the  usual  way
+       The  output is an integer that is set to one if internal recursion when
+       running pcre2_match() is implemented by recursive function  calls  that
+       use  the  system  stack  to remember their state. This is the usual way
        that PCRE2 is compiled. The output is zero if PCRE2 was compiled to use
        blocks of data on the heap instead of recursive function calls.
 
          PCRE2_CONFIG_UNICODE_VERSION
 
-       The where argument should point to a buffer that is at  least  24  code
-       units long. (The exact length needed can be found by calling pcre2_con-
-       fig() with where set to NULL.) If PCRE2 has been compiled without  Uni-
-       code  support,  the  buffer  is  filled with the text "Unicode not sup-
-       ported". Otherwise, the Unicode version string (for  example,  "7.0.0")
-       is  inserted.  The  number  of code units used is returned. This is the
-       length of the string plus one unit for the terminating zero.
+       The  where  argument  should point to a buffer that is at least 24 code
+       units long.  (The  exact  length  required  can  be  found  by  calling
+       pcre2_config()  with  where  set  to  NULL.) If PCRE2 has been compiled
+       without Unicode support, the buffer is filled with  the  text  "Unicode
+       not  supported".  Otherwise,  the  Unicode version string (for example,
+       "7.0.0") is inserted. The number of code units used is  returned.  This
+       is the length of the string plus one unit for the terminating zero.
 
          PCRE2_CONFIG_UNICODE
 
-       The output is an integer that is set  to  one  if  Unicode  support  is
-       available;  otherwise  it  is  set to zero. Unicode support implies UTF
+       The  output  is  an  integer  that  is set to one if Unicode support is
+       available; otherwise it is set to zero.  Unicode  support  implies  UTF
        support.
 
          PCRE2_CONFIG_VERSION
 
-       The where argument should point to a buffer that is at  least  12  code
-       units long. (The exact length needed can be found by calling pcre2_con-
-       fig() with where set to NULL.) The buffer is filled with the PCRE2 ver-
-       sion  string,  zero-terminated.  The  number  of  code  units  used  is
+       The  where  argument  should point to a buffer that is at least 12 code
+       units long.  (The  exact  length  required  can  be  found  by  calling
+       pcre2_config()  with  where set to NULL.) The buffer is filled with the
+       PCRE2 version string, zero-terminated. The number of code units used is
        returned. This is the length of the string plus one unit for the termi-
        nating zero.
 
@@ -974,49 +970,51 @@ COMPILING A PATTERN
 
        pcre2_code_free(pcre2_code *code);
 
-       This  function  compiles a pattern, defined by a pointer to a string of
-       code units and a length, into an internal form. If the pattern is zero-
-       terminated,  the  length  should be specified as PCRE2_ZERO_TERMINATED.
-       The function returns a pointer to a block of memory that  contains  the
-       compiled  pattern  and related data. The caller must free the memory by
-       calling pcre2_code_free() when it is no longer needed.
+       The pcre2_compile() function compiles a pattern into an internal  form.
+       The  pattern  is  defined  by a pointer to a string of code units and a
+       length, If the pattern is zero-terminated, the length can be  specified
+       as  PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of
+       memory that contains the compiled pattern and related data. The  caller
+       must  free the memory by calling pcre2_code_free() when it is no longer
+       needed.
 
-       If the compile  context  argument  ccontext  is  NULL,  the  memory  is
-       obtained  by  calling malloc(). Otherwise, it is obtained from the same
-       memory function that was used for the compile context.
+       If the compile context argument ccontext is NULL, memory for  the  com-
+       piled  pattern  is  obtained  by  calling  malloc().  Otherwise,  it is
+       obtained from the same memory function that was used  for  the  compile
+       context.
 
        The options argument contains various bit settings that affect the com-
-       pilation.  It  should be zero if no options are required. The available
-       options are described below. Some of them (in  particular,  those  that
-       are  compatible with Perl, but some others as well) can also be set and
-       unset from within the pattern (see  the  detailed  description  in  the
+       pilation. It should be zero if no options are required.  The  available
+       options  are  described  below. Some of them (in particular, those that
+       are compatible with Perl, but some others as well) can also be set  and
+       unset  from  within  the  pattern  (see the detailed description in the
        pcre2pattern documentation).
 
-       For  those options that can be different in different parts of the pat-
-       tern, the contents of the options argument specifies their settings  at
-       the  start  of  compilation.  The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK
+       For those options that can be different in different parts of the  pat-
+       tern,  the contents of the options argument specifies their settings at
+       the start of compilation.  The  PCRE2_ANCHORED  and  PCRE2_NO_UTF_CHECK
        options can be set at the time of matching as well as at compile time.
 
-       Other, less frequently required compile-time parameters  (for  example,
+       Other,  less  frequently required compile-time parameters (for example,
        the newline setting) can be provided in a compile context (as described
        above).
 
        If errorcode or erroroffset is NULL, pcre2_compile() returns NULL imme-
-       diately.  Otherwise, if compilation of a pattern fails, pcre2_compile()
+       diately. Otherwise, if compilation of a pattern fails,  pcre2_compile()
        returns NULL, having set these variables to an error code and an offset
-       (number   of   code   units)  within  the  pattern,  respectively.  The
-       pcre2_get_error_message() function provides a textual message for  each
+       (number  of  code  units)  within  the   pattern,   respectively.   The
+       pcre2_get_error_message()  function provides a textual message for each
        error code. Compilation errors are positive numbers, but UTF formatting
        errors are negative numbers. For an invalid UTF-8 or UTF-16 string, the
        offset is that of the first code unit of the failing character.
 
-       Some  errors are not detected until the whole pattern has been scanned;
-       in these cases, the offset passed back is the length  of  the  pattern.
-       Note  that  the  offset is in code units, not characters, even in a UTF
+       Some errors are not detected until the whole pattern has been  scanned;
+       in  these  cases,  the offset passed back is the length of the pattern.
+       Note that the offset is in code units, not characters, even  in  a  UTF
        mode. It may sometimes point into the middle of a UTF-8 or UTF-16 char-
        acter.
 
-       This  code  fragment shows a typical straightforward call to pcre2_com-
+       This code fragment shows a typical straightforward call  to  pcre2_com-
        pile():
 
          pcre2_code *re;
@@ -1030,158 +1028,158 @@ COMPILING A PATTERN
            &erroffset,             /* for error offset */
            NULL);                  /* no compile context */
 
-       The following names for option bits are defined in the  pcre2.h  header
+       The  following  names for option bits are defined in the pcre2.h header
        file:
 
          PCRE2_ANCHORED
 
        If this bit is set, the pattern is forced to be "anchored", that is, it
-       is constrained to match only at the first matching point in the  string
-       that  is being searched (the "subject string"). This effect can also be
-       achieved by appropriate constructs in the pattern itself, which is  the
+       is  constrained to match only at the first matching point in the string
+       that is being searched (the "subject string"). This effect can also  be
+       achieved  by appropriate constructs in the pattern itself, which is the
        only way to do it in Perl.
 
          PCRE2_ALLOW_EMPTY_CLASS
 
-       By  default, for compatibility with Perl, a closing square bracket that
-       immediately follows an opening one is treated as a data  character  for
-       the  class.  When  PCRE2_ALLOW_EMPTY_CLASS  is  set,  it terminates the
+       By default, for compatibility with Perl, a closing square bracket  that
+       immediately  follows  an opening one is treated as a data character for
+       the class. When  PCRE2_ALLOW_EMPTY_CLASS  is  set,  it  terminates  the
        class, which therefore contains no characters and so can never match.
 
          PCRE2_ALT_BSUX
 
-       This option request alternative handling  of  three  escape  sequences,
-       which  makes  PCRE2's  behaviour more like ECMAscript (aka JavaScript).
+       This  option  request  alternative  handling of three escape sequences,
+       which makes PCRE2's behaviour more like  ECMAscript  (aka  JavaScript).
        When it is set:
 
        (1) \U matches an upper case "U" character; by default \U causes a com-
        pile time error (Perl uses \U to upper case subsequent characters).
 
        (2) \u matches a lower case "u" character unless it is followed by four
-       hexadecimal digits, in which case the hexadecimal  number  defines  the
-       code  point  to match. By default, \u causes a compile time error (Perl
+       hexadecimal  digits,  in  which case the hexadecimal number defines the
+       code point to match. By default, \u causes a compile time  error  (Perl
        uses it to upper case the following character).
 
-       (3) \x matches a lower case "x" character unless it is followed by  two
-       hexadecimal  digits,  in  which case the hexadecimal number defines the
-       code point to match. By default, as in Perl, a  hexadecimal  number  is
+       (3)  \x matches a lower case "x" character unless it is followed by two
+       hexadecimal digits, in which case the hexadecimal  number  defines  the
+       code  point  to  match. By default, as in Perl, a hexadecimal number is
        always expected after \x, but it may have zero, one, or two digits (so,
        for example, \xz matches a binary zero character followed by z).
 
          PCRE2_AUTO_CALLOUT
 
-       If this bit  is  set,  pcre2_compile()  automatically  inserts  callout
+       If  this  bit  is  set,  pcre2_compile()  automatically inserts callout
        items, all with number 255, before each pattern item. For discussion of
        the callout facility, see the pcre2callout documentation.
 
          PCRE2_CASELESS
 
-       If this bit is set, letters in the pattern match both upper  and  lower
-       case  letters in the subject. It is equivalent to Perl's /i option, and
+       If  this  bit is set, letters in the pattern match both upper and lower
+       case letters in the subject. It is equivalent to Perl's /i option,  and
        it can be changed within a pattern by a (?i) option setting.
 
          PCRE2_DOLLAR_ENDONLY
 
-       If this bit is set, a dollar metacharacter in the pattern matches  only
-       at  the  end  of the subject string. Without this option, a dollar also
-       matches immediately before a newline at the end of the string (but  not
-       before  any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored
-       if PCRE2_MULTILINE is set. There is no equivalent  to  this  option  in
+       If  this bit is set, a dollar metacharacter in the pattern matches only
+       at the end of the subject string. Without this option,  a  dollar  also
+       matches  immediately before a newline at the end of the string (but not
+       before any other newlines). The PCRE2_DOLLAR_ENDONLY option is  ignored
+       if  PCRE2_MULTILINE  is  set.  There is no equivalent to this option in
        Perl, and no way to set it within a pattern.
 
          PCRE2_DOTALL
 
-       If  this  bit  is  set,  a dot metacharacter in the pattern matches any
-       character, including one that indicates a  newline.  However,  it  only
+       If this bit is set, a dot metacharacter  in  the  pattern  matches  any
+       character,  including  one  that  indicates a newline. However, it only
        ever matches one character, even if newlines are coded as CRLF. Without
        this option, a dot does not match when the current position in the sub-
-       ject  is  at  a newline. This option is equivalent to Perl's /s option,
+       ject is at a newline. This option is equivalent to  Perl's  /s  option,
        and it can be changed within a pattern by a (?s) option setting. A neg-
        ative class such as [^a] always matches newline characters, independent
        of the setting of this option.
 
          PCRE2_DUPNAMES
 
-       If this bit is set, names used to identify capturing  subpatterns  need
+       If  this  bit is set, names used to identify capturing subpatterns need
        not be unique. This can be helpful for certain types of pattern when it
-       is known that only one instance of the named  subpattern  can  ever  be
-       matched.  There  are  more details of named subpatterns below; see also
+       is  known  that  only  one instance of the named subpattern can ever be
+       matched. There are more details of named subpatterns  below;  see  also
        the pcre2pattern documentation.
 
          PCRE2_EXTENDED
 
-       If this bit is set, most white space  characters  in  the  pattern  are
-       totally  ignored  except when escaped or inside a character class. How-
-       ever, white space is not allowed within  sequences  such  as  (?>  that
+       If  this  bit  is  set,  most white space characters in the pattern are
+       totally ignored except when escaped or inside a character  class.  How-
+       ever,  white  space  is  not  allowed within sequences such as (?> that
        introduce various parenthesized subpatterns, nor within numerical quan-
-       tifiers such as {1,3}.  Ignorable white space is permitted  between  an
-       item  and a following quantifier and between a quantifier and a follow-
+       tifiers  such  as {1,3}.  Ignorable white space is permitted between an
+       item and a following quantifier and between a quantifier and a  follow-
        ing + that indicates possessiveness.
 
-       PCRE2_EXTENDED also causes characters between an unescaped # outside  a
-       character  class  and the next newline, inclusive, to be ignored, which
+       PCRE2_EXTENDED  also causes characters between an unescaped # outside a
+       character class and the next newline, inclusive, to be  ignored,  which
        makes it possible to include comments inside complicated patterns. Note
-       that  the  end of this type of comment is a literal newline sequence in
+       that the end of this type of comment is a literal newline  sequence  in
        the pattern; escape sequences that happen to represent a newline do not
-       count.  PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be
+       count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can  be
        changed within a pattern by a (?x) option setting.
 
        Which characters are interpreted as newlines can be specified by a set-
-       ting  in  the compile context that is passed to pcre2_compile() or by a
-       special sequence at the start of the pattern, as described in the  sec-
-       tion  entitled "Newline conventions" in the pcre2pattern documentation.
+       ting in the compile context that is passed to pcre2_compile() or  by  a
+       special  sequence at the start of the pattern, as described in the sec-
+       tion entitled "Newline conventions" in the pcre2pattern  documentation.
        A default is defined when PCRE2 is built.
 
          PCRE2_FIRSTLINE
 
-       If this option is set, an  unanchored  pattern  is  required  to  match
-       before  or  at  the  first  newline  in  the subject string, though the
+       If  this  option  is  set,  an  unanchored pattern is required to match
+       before or at the first  newline  in  the  subject  string,  though  the
        matched text may continue over the newline.
 
          PCRE2_MATCH_UNSET_BACKREF
 
-       If this option is set, a back reference to an  unset  subpattern  group
-       matches  an  empty  string (by default this causes the current matching
-       alternative to fail).  A pattern such as  (\1)(a)  succeeds  when  this
-       option  is set (assuming it can find an "a" in the subject), whereas it
-       fails by default, for Perl compatibility.  Setting  this  option  makes
+       If  this  option  is set, a back reference to an unset subpattern group
+       matches an empty string (by default this causes  the  current  matching
+       alternative  to  fail).   A  pattern such as (\1)(a) succeeds when this
+       option is set (assuming it can find an "a" in the subject), whereas  it
+       fails  by  default,  for  Perl compatibility. Setting this option makes
        PCRE2 behave more like ECMAscript (aka JavaScript).
 
          PCRE2_MULTILINE
 
-       By  default,  for  the purposes of matching "start of line" and "end of
-       line", PCRE2 treats the subject string as consisting of a  single  line
-       of  characters,  even  if  it actually contains newlines. The "start of
-       line" metacharacter (^) matches only at the start of  the  string,  and
-       the  "end  of  line"  metacharacter  ($) matches only at the end of the
+       By default, for the purposes of matching "start of line"  and  "end  of
+       line",  PCRE2  treats the subject string as consisting of a single line
+       of characters, even if it actually contains  newlines.  The  "start  of
+       line"  metacharacter  (^)  matches only at the start of the string, and
+       the "end of line" metacharacter ($) matches only  at  the  end  of  the
        string,  or  before  a  terminating  newline  (except  when  PCRE2_DOL-
-       LAR_ENDONLY  is  set).  Note, however, that unless PCRE2_DOTALL is set,
+       LAR_ENDONLY is set). Note, however, that unless  PCRE2_DOTALL  is  set,
        the "any character" metacharacter (.) does not match at a newline. This
        behaviour (for ^, $, and dot) is the same as Perl.
 
-       When  PCRE2_MULTILINE  it is set, the "start of line" and "end of line"
-       constructs match immediately following or immediately  before  internal
-       newlines  in  the  subject string, respectively, as well as at the very
-       start and end. This is equivalent to Perl's /m option, and  it  can  be
+       When PCRE2_MULTILINE it is set, the "start of line" and "end  of  line"
+       constructs  match  immediately following or immediately before internal
+       newlines in the subject string, respectively, as well as  at  the  very
+       start  and  end.  This is equivalent to Perl's /m option, and it can be
        changed within a pattern by a (?m) option setting. If there are no new-
-       lines in a subject string, or no occurrences of ^ or $  in  a  pattern,
+       lines  in  a  subject string, or no occurrences of ^ or $ in a pattern,
        setting PCRE2_MULTILINE has no effect.
 
          PCRE2_NEVER_UCP
 
-       This  option  locks  out the use of Unicode properties for handling \B,
+       This option locks out the use of Unicode properties  for  handling  \B,
        \b, \D, \d, \S, \s, \W, \w, and some of the POSIX character classes, as
-       described  for  the  PCRE2_UCP option below. In particular, it prevents
-       the creator of the pattern from enabling this facility by starting  the
-       pattern  with  (*UCP).  This may be useful in applications that process
-       patterns from external sources. The  option  combination  PCRE_UCP  and
+       described for the PCRE2_UCP option below. In  particular,  it  prevents
+       the  creator of the pattern from enabling this facility by starting the
+       pattern with (*UCP). This may be useful in  applications  that  process
+       patterns  from  external  sources.  The option combination PCRE_UCP and
        PCRE_NEVER_UCP causes an error.
 
          PCRE2_NEVER_UTF
 
-       This  option  locks out interpretation of the pattern as UTF-8, UTF-16,
+       This option locks out interpretation of the pattern as  UTF-8,  UTF-16,
        or UTF-32, depending on which library is in use. In particular, it pre-
-       vents  the  creator of the pattern from switching to UTF interpretation
+       vents the creator of the pattern from switching to  UTF  interpretation
        by starting the pattern with (*UTF). This may be useful in applications
        that  process  patterns  from  external  sources.  The  combination  of
        PCRE2_UTF and PCRE2_NEVER_UTF causes an error.
@@ -1189,98 +1187,99 @@ COMPILING A PATTERN
          PCRE2_NO_AUTO_CAPTURE
 
        If this option is set, it disables the use of numbered capturing paren-
-       theses  in the pattern. Any opening parenthesis that is not followed by
-       ? behaves as if it were followed by ?: but named parentheses can  still
-       be  used  for  capturing  (and  they acquire numbers in the usual way).
+       theses in the pattern. Any opening parenthesis that is not followed  by
+       ?  behaves as if it were followed by ?: but named parentheses can still
+       be used for capturing (and they acquire  numbers  in  the  usual  way).
        There is no equivalent of this option in Perl.
 
          PCRE2_NO_AUTO_POSSESS
 
        If this option is set, it disables "auto-possessification", which is an
-       optimization  that,  for example, turns a+b into a++b in order to avoid
-       backtracks into a+ that can never be successful. However,  if  callouts
-       are  in  use,  auto-possessification means that some callouts are never
+       optimization that, for example, turns a+b into a++b in order  to  avoid
+       backtracks  into  a+ that can never be successful. However, if callouts
+       are in use, auto-possessification means that some  callouts  are  never
        taken. You can set this option if you want the matching functions to do
-       a  full  unoptimized  search and run all the callouts, but it is mainly
+       a full unoptimized search and run all the callouts, but  it  is  mainly
        provided for testing purposes.
 
          PCRE2_NO_START_OPTIMIZE
 
-       This is an option whose main effect is at matching time.  It  does  not
+       This  is  an  option whose main effect is at matching time. It does not
        change what pcre2_compile() generates, but it does affect the output of
        the JIT compiler.
 
-       There are a number of optimizations that may occur at the  start  of  a
-       match,  in  order  to speed up the process. For example, if it is known
-       that an unanchored match must start  with  a  specific  character,  the
-       matching  code searches the subject for that character, and fails imme-
-       diately if it cannot find it, without actually running the main  match-
-       ing  function.  This means that a special item such as (*COMMIT) at the
-       start of a pattern is not considered until after  a  suitable  starting
-       point  for  the  match  has  been found. Also, when callouts or (*MARK)
-       items are in use, these "start-up" optimizations can cause them  to  be
-       skipped  if  the pattern is never actually used. The start-up optimiza-
-       tions are in effect a pre-scan of the subject that takes  place  before
+       There  are  a  number of optimizations that may occur at the start of a
+       match, in order to speed up the process. For example, if  it  is  known
+       that  an  unanchored  match  must  start with a specific character, the
+       matching code searches the subject for that character, and fails  imme-
+       diately  if it cannot find it, without actually running the main match-
+       ing function. This means that a special item such as (*COMMIT)  at  the
+       start  of  a  pattern is not considered until after a suitable starting
+       point for the match has been found.  Also,  when  callouts  or  (*MARK)
+       items  are  in use, these "start-up" optimizations can cause them to be
+       skipped if the pattern is never actually used. The  start-up  optimiza-
+       tions  are  in effect a pre-scan of the subject that takes place before
        the pattern is run.
 
        The PCRE2_NO_START_OPTIMIZE option disables the start-up optimizations,
-       possibly causing performance to suffer,  but  ensuring  that  in  cases
-       where  the  result is "no match", the callouts do occur, and that items
+       possibly  causing  performance  to  suffer,  but ensuring that in cases
+       where the result is "no match", the callouts do occur, and  that  items
        such as (*COMMIT) and (*MARK) are considered at every possible starting
        position in the subject string.
 
-       Setting  PCRE2_NO_START_OPTIMIZE  may  change the outcome of a matching
+       Setting PCRE2_NO_START_OPTIMIZE may change the outcome  of  a  matching
        operation.  Consider the pattern
 
          (*COMMIT)ABC
 
-       When this is compiled, PCRE2 records the fact that a match  must  start
-       with  the  character  "A".  Suppose the subject string is "DEFABC". The
-       start-up optimization scans along the subject, finds "A" and  runs  the
-       first  match attempt from there. The (*COMMIT) item means that the pat-
-       tern must match the current starting position, which in this  case,  it
-       does.  However,  if  the same match is run with PCRE2_NO_START_OPTIMIZE
-       set, the initial scan along the subject string  does  not  happen.  The
-       first  match  attempt  is  run  starting  from "D" and when this fails,
-       (*COMMIT) prevents any further matches  being  tried,  so  the  overall
+       When  this  is compiled, PCRE2 records the fact that a match must start
+       with the character "A". Suppose the subject  string  is  "DEFABC".  The
+       start-up  optimization  scans along the subject, finds "A" and runs the
+       first match attempt from there. The (*COMMIT) item means that the  pat-
+       tern  must  match the current starting position, which in this case, it
+       does. However, if the same match is  run  with  PCRE2_NO_START_OPTIMIZE
+       set,  the  initial  scan  along the subject string does not happen. The
+       first match attempt is run starting  from  "D"  and  when  this  fails,
+       (*COMMIT)  prevents  any  further  matches  being tried, so the overall
        result is "no match". There are also other start-up optimizations.  For
        example, a minimum length for the subject may be recorded. Consider the
        pattern
 
          (*MARK:A)(X|Y)
 
-       The  minimum  length  for  a  match is one character. If the subject is
+       The minimum length for a match is one  character.  If  the  subject  is
        "ABC", there will be attempts to match "ABC", "BC", and "C". An attempt
        to match an empty string at the end of the subject does not take place,
-       because PCRE2 knows that the subject is  now  too  short,  and  so  the
-       (*MARK)  is  never encountered. In this case, the optimization does not
+       because  PCRE2  knows  that  the  subject  is now too short, and so the
+       (*MARK) is never encountered. In this case, the optimization  does  not
        affect the overall match result, which is still "no match", but it does
        affect the auxiliary information that is returned.
 
          PCRE2_NO_UTF_CHECK
 
-       When  PCRE2_UTF  is set, the validity of the pattern as a UTF string is
-       automatically checked. There are  discussions  about  the  validity  of
-       UTF-8  strings,  UTF-16 strings, and UTF-32 strings in the pcre2unicode
+       When PCRE2_UTF is set, the validity of the pattern as a UTF  string  is
+       automatically  checked.  There  are  discussions  about the validity of
+       UTF-8 strings, UTF-16 strings, and UTF-32 strings in  the  pcre2unicode
        document.  If an invalid UTF sequence is found, pcre2_compile() returns
        a negative error code.
 
        If you know that your pattern is valid, and you want to skip this check
-       for performance reasons, you can  set  the  PCRE2_NO_UTF_CHECK  option.
-       When  it  is set, the effect of passing an invalid UTF string as a pat-
-       tern is undefined. It may cause your program to  crash  or  loop.  Note
-       that   this   option   can   also   be   passed  to  pcre2_match()  and
+       for  performance  reasons,  you  can set the PCRE2_NO_UTF_CHECK option.
+       When it is set, the effect of passing an invalid UTF string as  a  pat-
+       tern  is  undefined.  It  may cause your program to crash or loop. Note
+       that  this  option  can   also   be   passed   to   pcre2_match()   and
        pcre_dfa_match(), to suppress validity checking of the subject string.
 
          PCRE2_UCP
 
        This option changes the way PCRE2 processes \B, \b, \D, \d, \S, \s, \W,
-       \w,  and  some  of  the POSIX character classes. By default, only ASCII
-       characters are recognized, but if PCRE2_UCP is set, Unicode  properties
-       are  used instead to classify characters. More details are given in the
+       \w, and some of the POSIX character classes.  By  default,  only  ASCII
+       characters  are recognized, but if PCRE2_UCP is set, Unicode properties
+       are used instead to classify characters. More details are given in  the
        section on generic character types in the pcre2pattern page. If you set
-       PCRE2_UCP,  matching one of the items it affects takes much longer. The
-       option is available only if PCRE2 has been compiled with UTF support.
+       PCRE2_UCP, matching one of the items it affects takes much longer.  The
+       option  is  available only if PCRE2 has been compiled with Unicode sup-
+       port.
 
          PCRE2_UNGREEDY
 
@@ -1293,18 +1292,19 @@ COMPILING A PATTERN
 
        This  option  causes  PCRE2  to regard both the pattern and the subject
        strings that are subsequently processed as strings  of  UTF  characters
-       instead of single-code-unit strings. However, it is available only when
-       PCRE2 is built to include UTF support. If not, the use of  this  option
-       provokes  an error. Details of how this option changes the behaviour of
-       PCRE2 are given in the pcre2unicode page.
+       instead  of  single-code-unit  strings.  It  is available when PCRE2 is
+       built to include Unicode support (which is  the  default).  If  Unicode
+       support  is  not  available,  the use of this option provokes an error.
+       Details of how this option changes the behaviour of PCRE2 are given  in
+       the pcre2unicode page.
 
 
 COMPILATION ERROR CODES
 
-       There are over 80 positive error codes that pcre2_compile() may  return
+       There  are over 80 positive error codes that pcre2_compile() may return
        if it finds an error in the pattern. There are also some negative error
-       codes that are used for invalid UTF strings.  These  are  the  same  as
-       given  by pcre2_match() and pcre2_dfa_match(), and are described in the
+       codes  that  are  used  for  invalid UTF strings. These are the same as
+       given by pcre2_match() and pcre2_dfa_match(), and are described in  the
        pcre2unicode page. The pcre2_get_error_message() function can be called
        to obtain a textual error message from any error code.
 
@@ -1328,31 +1328,30 @@ JUST-IN-TIME (JIT) COMPILATION
 
        void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack);
 
-       These  functions  provide  support  for  JIT compilation, which, if the
-       just-in-time compiler is available, further processes a  compiled  pat-
+       These functions provide support for  JIT  compilation,  which,  if  the
+       just-in-time  compiler  is available, further processes a compiled pat-
        tern into machine code that executes much faster than the pcre2_match()
-       interpretive matching function. Full details are given in the  pcre2jit
+       interpretive  matching function. Full details are given in the pcre2jit
        documentation.
 
-       JIT  compilation  is  a heavyweight optimization. It can take some time
-       for patterns to be analyzed, and for one-off matches  and  simple  pat-
-       terns  the benefit of faster execution might be offset by a much slower
-       compilation time.  Most, but not all patterns can be optimized  by  the
+       JIT compilation is a heavyweight optimization. It can  take  some  time
+       for  patterns  to  be analyzed, and for one-off matches and simple pat-
+       terns the benefit of faster execution might be offset by a much  slower
+       compilation  time.   Most, but not all patterns can be optimized by the
        JIT compiler.
 
 
 LOCALE SUPPORT
 
-       PCRE2  handles caseless matching, and determines whether characters are
-       letters, digits, or whatever, by reference to a set of tables,  indexed
-       by  character  code  point.  When  running  in UTF-8 mode, or using the
-       16-bit or 32-bit libraries, this applies only to characters  with  code
-       points less than 256. By default, higher-valued code points never match
-       escapes such as \w or \d. However, if PCRE2 is built with UTF  support,
-       all  characters  can  be  tested with \p and \P, or, alternatively, the
-       PCRE2_UCP option can be set when a pattern is compiled; this causes  \w
-       and  friends  to  use  Unicode property support instead of the built-in
-       tables.
+       PCRE2 handles caseless matching, and determines whether characters  are
+       letters,  digits, or whatever, by reference to a set of tables, indexed
+       by character code point. This applies only  to  characters  whose  code
+       points  are  less than 256. By default, higher-valued code points never
+       match escapes such as \w or \d.  However, if PCRE2 is  built  with  UTF
+       support,  all  characters  can  be  tested with \p and \P, or, alterna-
+       tively, the PCRE2_UCP option can be set when  a  pattern  is  compiled;
+       this  causes  \w and friends to use Unicode property support instead of
+       the built-in tables.
 
        The use of locales with Unicode is discouraged.  If  you  are  handling
        characters  with  code  points  greater than 128, you should either use
@@ -1463,31 +1462,30 @@ INFORMATION ABOUT A COMPILED PATTERN
          PCRE2_INFO_BSR
 
        The output is a uint32_t whose value indicates what character sequences
-       the  \R  escape sequence matches by default. A value of 0 means that \R
-       matches any Unicode line ending sequence; a value of 1  means  that  \R
-       matches only CR, LF, or CRLF. The default can be overridden when a pat-
-       tern is matched.
+       the \R escape sequence matches. A value of PCRE2_BSR_UNICODE means that
+       \R matches any Unicode line ending sequence; a value of  PCRE2_BSR_ANY-
+       CRLF means that \R matches only CR, LF, or CRLF.
 
          PCRE2_INFO_CAPTURECOUNT
 
-       Return the number of capturing subpatterns in the  pattern.  The  third
+       Return  the  number  of capturing subpatterns in the pattern. The third
        argument should point to an uint32_t variable.
 
          PCRE2_INFO_FIRSTCODETYPE
 
        Return information about the first code unit of any matched string, for
-       a non-anchored pattern. The third argument should point to an  uint32_t
+       a  non-anchored pattern. The third argument should point to an uint32_t
        variable.
 
-       If  there  is  a  fixed first value, for example, the letter "c" from a
-       pattern such as (cat|cow|coyote), 1  is  returned,  and  the  character
-       value  can  be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is no
+       If there is a fixed first value, for example, the  letter  "c"  from  a
+       pattern  such  as  (cat|cow|coyote),  1  is returned, and the character
+       value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there  is  no
        fixed first value, and if either
 
        (a) the pattern was compiled with the PCRE2_MULTILINE option, and every
        branch starts with "^", or
 
-       (b)  every  branch  of the pattern starts with ".*" and PCRE2_DOTALL is
+       (b) every branch of the pattern starts with ".*"  and  PCRE2_DOTALL  is
        not set (if it were set, the pattern would be anchored),
 
        2 is returned, indicating that the pattern matches only at the start of
@@ -1496,99 +1494,99 @@ INFORMATION ABOUT A COMPILED PATTERN
 
          PCRE2_INFO_FIRSTCODEUNIT
 
-       Return the value of the first code unit of any matched  string  in  the
+       Return  the  value  of the first code unit of any matched string in the
        situation where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0.
-       The third argument should point to an uint32_t variable. In  the  8-bit
-       library,  the  value is always less than 256. In the 16-bit library the
-       value can be up to 0xffff. In the 32-bit library  in  UTF-32  mode  the
+       The  third  argument should point to an uint32_t variable. In the 8-bit
+       library, the value is always less than 256. In the 16-bit  library  the
+       value  can  be  up  to 0xffff. In the 32-bit library in UTF-32 mode the
        value can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32
        mode.
 
          PCRE2_INFO_FIRSTBITMAP
 
-       In the absence of a single first code unit for a non-anchored  pattern,
-       pcre2_compile()  may construct a 256-bit table that defines a fixed set
-       of values for the first code unit in any match. For example, a  pattern
-       that  starts  with  [abc]  results in a table with three bits set. When
-       code unit values greater than 255 are supported, the flag bit  for  255
-       means  "any  code unit of value 255 or above". If such a table was con-
-       structed, a pointer to it is returned. Otherwise NULL is returned.  The
+       In  the absence of a single first code unit for a non-anchored pattern,
+       pcre2_compile() may construct a 256-bit table that defines a fixed  set
+       of  values for the first code unit in any match. For example, a pattern
+       that starts with [abc] results in a table with  three  bits  set.  When
+       code  unit  values greater than 255 are supported, the flag bit for 255
+       means "any code unit of value 255 or above". If such a table  was  con-
+       structed,  a pointer to it is returned. Otherwise NULL is returned. The
        third argument should point to an const uint8_t * variable.
 
          PCRE2_INFO_HASCRORLF
 
-       Return  1  if  the  pattern  contains any explicit matches for CR or LF
+       Return 1 if the pattern contains any explicit  matches  for  CR  or  LF
        characters, otherwise 0. The third argument should point to an uint32_t
-       variable.  An explicit match is either a literal CR or LF character, or
+       variable. An explicit match is either a literal CR or LF character,  or
        \r or \n.
 
          PCRE2_INFO_JCHANGED
 
-       Return 1 if the (?J) or (?-J) option setting is used  in  the  pattern,
-       otherwise  0.  The third argument should point to an uint32_t variable.
-       (?J) and (?-J) set and unset the local PCRE2_DUPNAMES  option,  respec-
+       Return  1  if  the (?J) or (?-J) option setting is used in the pattern,
+       otherwise 0. The third argument should point to an  uint32_t  variable.
+       (?J)  and  (?-J) set and unset the local PCRE2_DUPNAMES option, respec-
        tively.
 
          PCRE2_INFO_JITSIZE
 
-       If  the  compiled  pattern was successfully processed by pcre2_jit_com-
-       pile(), return the size of the  JIT  compiled  code,  otherwise  return
+       If the compiled pattern was successfully  processed  by  pcre2_jit_com-
+       pile(),  return  the  size  of  the JIT compiled code, otherwise return
        zero. The third argument should point to a size_t variable.
 
          PCRE2_INFO_LASTCODETYPE
 
-       Returns  1 if there is a rightmost literal code unit that must exist in
-       any matched string, other than at its start. The third argument  should
-       point  to  an  uint32_t  variable.  If  there  is  no  such value, 0 is
-       returned. When 1 is  returned,  the  code  unit  value  itself  can  be
+       Returns 1 if there is a rightmost literal code unit that must exist  in
+       any  matched string, other than at its start. The third argument should
+       point to an uint32_t  variable.  If  there  is  no  such  value,  0  is
+       returned.  When  1  is  returned,  the  code  unit  value itself can be
        retrieved using PCRE2_INFO_LASTCODEUNIT.
 
        For anchored patterns, a last literal value is recorded only if it fol-
-       lows something  of  variable  length.  For  example,  for  the  pattern
-       /^a\d+z\d+/   the   returned   value  is  1  (with  "z"  returned  from
+       lows  something  of  variable  length.  For  example,  for  the pattern
+       /^a\d+z\d+/  the  returned  value  is  1  (with   "z"   returned   from
        PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ the returned value is 0.
 
          PCRE2_INFO_LASTCODEUNIT
 
-       Return the value of the rightmost literal data unit that must exist  in
-       any  matched  string, other than at its start, if such a value has been
-       recorded. The third argument should point to an uint32_t  variable.  If
+       Return  the value of the rightmost literal data unit that must exist in
+       any matched string, other than at its start, if such a value  has  been
+       recorded.  The  third argument should point to an uint32_t variable. If
        there is no such value, 0 is returned.
 
          PCRE2_INFO_MATCHEMPTY
 
-       Return  1  if  the  pattern can match an empty string, otherwise 0. The
+       Return 1 if the pattern can match an empty  string,  otherwise  0.  The
        third argument should point to an uint32_t variable.
 
          PCRE2_INFO_MATCHLIMIT
 
-       If the pattern set a match limit by  including  an  item  of  the  form
-       (*LIMIT_MATCH=nnnn)  at  the  start,  the  value is returned. The third
-       argument should point to an unsigned 32-bit integer. If no  such  value
-       has  been  set,  the  call  to  pcre2_pattern_info()  returns the error
+       If  the  pattern  set  a  match  limit by including an item of the form
+       (*LIMIT_MATCH=nnnn) at the start, the  value  is  returned.  The  third
+       argument  should  point to an unsigned 32-bit integer. If no such value
+       has been set,  the  call  to  pcre2_pattern_info()  returns  the  error
        PCRE2_ERROR_UNSET.
 
          PCRE2_INFO_MAXLOOKBEHIND
 
        Return the number of characters (not code units) in the longest lookbe-
-       hind  assertion  in  the pattern. The third argument should point to an
-       unsigned 32-bit integer. This information is useful when  doing  multi-
-       segment  matching  using the partial matching facilities. Note that the
+       hind assertion in the pattern. The third argument should  point  to  an
+       unsigned  32-bit  integer. This information is useful when doing multi-
+       segment matching using the partial matching facilities. Note  that  the
        simple assertions \b and \B require a one-character lookbehind. \A also
-       registers  a  one-character  lookbehind,  though  it  does not actually
-       inspect the previous character. This is to ensure  that  at  least  one
-       character  from  the old segment is retained when a new segment is pro-
+       registers a one-character  lookbehind,  though  it  does  not  actually
+       inspect  the  previous  character.  This is to ensure that at least one
+       character from the old segment is retained when a new segment  is  pro-
        cessed. Otherwise, if there are no lookbehinds in the pattern, \A might
        match incorrectly at the start of a new segment.
 
          PCRE2_INFO_MINLENGTH
 
-       If  a  minimum  length  for  matching subject strings was computed, its
-       value is returned. Otherwise the returned value is 0. The  value  is  a
-       number  of characters, which in UTF mode may be different from the num-
-       ber of code units.  The third argument  should  point  to  an  uint32_t
-       variable.  The  value  is  a  lower bound to the length of any matching
-       string. There may not be any strings of that length  that  do  actually
+       If a minimum length for matching  subject  strings  was  computed,  its
+       value  is  returned.  Otherwise the returned value is 0. The value is a
+       number of characters, which in UTF mode may be different from the  num-
+       ber  of  code  units.   The  third argument should point to an uint32_t
+       variable. The value is a lower bound to  the  length  of  any  matching
+       string.  There  may  not be any strings of that length that do actually
        match, but every string that does match is at least that long.
 
          PCRE2_INFO_NAMECOUNT
@@ -1596,26 +1594,27 @@ INFORMATION ABOUT A COMPILED PATTERN
          PCRE2_INFO_NAMETABLE
 
        PCRE2 supports the use of named as well as numbered capturing parenthe-
-       ses. The names are just an additional way of identifying the  parenthe-
+       ses.  The names are just an additional way of identifying the parenthe-
        ses, which still acquire numbers. Several convenience functions such as
-       pcre2_substring_get_byname() are provided for extracting captured  sub-
-       strings  by  name. It is also possible to extract the data directly, by
-       first converting the name to a number in order to  access  the  correct
-       pointers  in the output vector (described with pcre2_match() below). To
-       do the conversion, you need to use the  name-to-number  map,  which  is
+       pcre2_substring_get_byname()  are provided for extracting captured sub-
+       strings by name. It is also possible to extract the data  directly,  by
+       first  converting  the  name to a number in order to access the correct
+       pointers in the output vector (described with pcre2_match() below).  To
+       do  the  conversion,  you  need to use the name-to-number map, which is
        described by these three values.
 
-       The  map  consists  of a number of fixed-size entries. PCRE2_INFO_NAME-
-       COUNT gives the number of entries, and  PCRE2_INFO_NAMEENTRYSIZE  gives
-       the  size  of  each  entry;  both of these return a uint32_t value. The
-       entry   size   depends   on   the   length   of   the   longest   name.
+       The map consists of a number of  fixed-size  entries.  PCRE2_INFO_NAME-
+       COUNT  gives  the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives
+       the size of each entry in code units; both of these return  a  uint32_t
+       value. The entry size depends on the length of the longest name.
+
        PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table.
        This is a PCRE2_SPTR pointer to a block of code  units.  In  the  8-bit
        library,  the  first two bytes of each entry are the number of the cap-
        turing parenthesis, most significant byte first. In the 16-bit library,
-       the  pointer  points  to 16-bit data units, the first of which contains
+       the  pointer  points  to 16-bit code units, the first of which contains
        the parenthesis number. In the 32-bit library, the  pointer  points  to
-       32-bit  data units, the first of which contains the parenthesis number.
+       32-bit  code units, the first of which contains the parenthesis number.
        The rest of the entry is the corresponding name, zero terminated.
 
        The names are in alphabetical order. If (?| is used to create  multiple
@@ -1653,35 +1652,34 @@ INFORMATION ABOUT A COMPILED PATTERN
 
          PCRE2_INFO_NEWLINE
 
-       The  output  is  a uint32_t whose value specifies the default character
-       sequence that will be recognized as meaning "newline"  while  matching.
-       The values are:
+       The output is a uint32_t with one of the following values:
 
-         1  Carriage return (CR)
-         2  Linefeed (LF)
-         3  Carriage return, linefeed (CRLF)
-         4  Any Unicode line ending
-         5  Any of CR, LF, or CRLF
+         PCRE2_NEWLINE_CR       Carriage return (CR)
+         PCRE2_NEWLINE_LF       Linefeed (LF)
+         PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
+         PCRE2_NEWLINE_ANY      Any Unicode line ending
+         PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
 
-       The default can be overridden when a pattern is matched.
+       This  specifies  the default character sequence that will be recognized
+       as meaning "newline" while matching.
 
          PCRE2_INFO_RECURSIONLIMIT
 
-       If  the  pattern set a recursion limit by including an item of the form
-       (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The  third
-       argument  should  point to an unsigned 32-bit integer. If no such value
-       has been set,  the  call  to  pcre2_pattern_info()  returns  the  error
+       If the pattern set a recursion limit by including an item of  the  form
+       (*LIMIT_RECURSION=nnnn)  at the start, the value is returned. The third
+       argument should point to an unsigned 32-bit integer. If no  such  value
+       has  been  set,  the  call  to  pcre2_pattern_info()  returns the error
        PCRE2_ERROR_UNSET.
 
          PCRE2_INFO_SIZE
 
-       Return  the  size  of  the  compiled  pattern  in  bytes (for all three
-       libraries). The third argument should point to a size_t variable.  This
-       value  does  not  include  the size of the pcre2_code structure that is
+       Return the size of  the  compiled  pattern  in  bytes  (for  all  three
+       libraries).  The third argument should point to a size_t variable. This
+       value does not include the size of the  pcre2_code  structure  that  is
        returned by pcre_compile(). The value that is used when pcre2_compile()
-       is  getting  memory  in  which  to place the compiled data is the value
+       is getting memory in which to place the  compiled  data  is  the  value
        returned by this option plus the size of the pcre2_code structure. Pro-
-       cessing  a  pattern  with  the  JIT  compiler  does not alter the value
+       cessing a pattern with the  JIT  compiler  does  not  alter  the  value
        returned by this option.
 
 
@@ -1695,39 +1693,40 @@ THE MATCH DATA BLOCK
 
        void pcre2_match_data_free(pcre2_match_data *match_data);
 
-       Information about successful and unsuccessful matches is  placed  in  a
-       match  data  block,  which  is  an opaque structure that is accessed by
-       function calls. In particular, the match data block contains  a  vector
-       of  offsets into the subject string that define the matched part of the
-       subject and any substrings that were capured. This is know as the ovec-
-       tor.
+       Information  about  successful  and unsuccessful matches is placed in a
+       match data block, which is an opaque  structure  that  is  accessed  by
+       function  calls.  In particular, the match data block contains a vector
+       of offsets into the subject string that define the matched part of  the
+       subject  and  any  substrings  that  were captured. This is know as the
+       ovector.
 
-       Before  calling  pcre2_match()  or  pcre2_dfa_match() you must create a
-       match data block by calling one of the creation  functions  above.  For
-       pcre2_match_data_create(), the first argument is the number of pairs of
-       offsets in the ovector. One pair of offsets is required to identify the
-       string  that matched the whole pattern, with another pair for each cap-
-       tured substring. For example, a value of  4  creates  enough  space  to
-       record  the  matched  portion  of  the subject plus three captured sub-
-       strings.   A   minimum   of   at   least   1   pair   is   imposed   by
+       Before calling pcre2_match(), pcre2_dfa_match(),  or  pcre2_jit_match()
+       you must create a match data block by calling one of the creation func-
+       tions above. For pcre2_match_data_create(), the first argument  is  the
+       number  of  pairs  of  offsets  in  the ovector. One pair of offsets is
+       required to identify the string that matched the  whole  pattern,  with
+       another  pair  for  each  captured substring. For example, a value of 4
+       creates enough space to record the matched portion of the subject  plus
+       three  captured  substrings. A minimum of at least 1 pair is imposed by
        pcre2_match_data_create(), so it is always possible to return the over-
        all matched string.
 
-       For pcre2_match_data_create_from_pattern(), the  first  argument  is  a
-       pointer  to  a compiled pattern. In this case the ovector is created to
-       be exactly the right size to hold all the substrings  a  pattern  might
+       For  pcre2_match_data_create_from_pattern(),  the  first  argument is a
+       pointer to a compiled pattern. In this case the ovector is  created  to
+       be  exactly  the  right size to hold all the substrings a pattern might
        capture.
 
-       The  second  argument of both these functions ia a pointer to a general
-       context, which can specify custom memory management for  obtaining  the
-       memory  for  the  match  data block. If you are not using custom memory
+       The second argument of both these functions is a pointer to  a  general
+       context,  which  can specify custom memory management for obtaining the
+       memory for the match data block. If you are  not  using  custom  memory
        management, pass NULL.
 
-       A match data block can be used many times, with the same  or  different
-       compiled  patterns.  When it is no longer needed, it should be freed by
-       calling pcre2_match_data_free(). How  to  extract  information  from  a
-       match  data  block after a match operation is described in the sections
-       on matched strings and other match data below.
+       A  match  data block can be used many times, with the same or different
+       compiled patterns. When it is no longer needed, it should be  freed  by
+       calling  pcre2_match_data_free().  You  can  extract information from a
+       match data block after a match operation has finished, using  functions
+       that  are  described in the sections on matched strings and other match
+       data below.
 
 
 MATCHING A PATTERN: THE TRADITIONAL FUNCTION
@@ -1826,12 +1825,10 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
        PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and  PCRE2_PARTIAL_SOFT.  Their
        action is described below.
 
-       If  the  pattern  was  successfully processed by the just-in-time (JIT)
-       compiler, the only supported options for matching using  the  JIT  code
-       are PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
-       PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT.  If  an
-       unsupported  option  is  used,  JIT matching is disabled and the normal
-       interpretive code in pcre2_match() is run.
+       Setting  PCRE2_ANCHORED  at match time is not supported by the just-in-
+       time (JIT) compiler. If it is set, JIT matching  is  disabled  and  the
+       normal interpretive code in pcre2_match() is run. The remaining options
+       are supported for JIT matching.
 
          PCRE2_ANCHORED
 
@@ -1845,18 +1842,18 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
 
        This option specifies that first character of the subject string is not
        the  beginning  of  a  line, so the circumflex metacharacter should not
-       match before it. Setting this without PCRE2_MULTILINE (at compile time)
-       causes  circumflex  never to match. This option affects only the behav-
-       iour of the circumflex metacharacter. It does not affect \A.
+       match before it. Setting this without  having  set  PCRE2_MULTILINE  at
+       compile time causes circumflex never to match. This option affects only
+       the behaviour of the circumflex metacharacter. It does not affect \A.
 
          PCRE2_NOTEOL
 
        This option specifies that the end of the subject string is not the end
        of  a line, so the dollar metacharacter should not match it nor (except
        in multiline mode) a newline immediately before it. Setting this  with-
-       out  PCRE2_MULTILINE  (at  compile  time) causes dollar never to match.
-       This option affects only the behaviour of the dollar metacharacter.  It
-       does not affect \Z or \z.
+       out  having  set PCRE2_MULTILINE at compile time causes dollar never to
+       match. This option affects only the behaviour of the dollar metacharac-
+       ter. It does not affect \Z or \z.
 
          PCRE2_NOTEMPTY
 
@@ -1869,14 +1866,16 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
 
        is applied to a string not beginning with "a" or  "b",  it  matches  an
        empty string at the start of the subject. With PCRE2_NOTEMPTY set, this
-       match is not valid, so PCRE2  searches  further  into  the  string  for
-       occurrences of "a" or "b".
+       match is not valid, so pcre2_match() searches further into  the  string
+       for occurrences of "a" or "b".
 
          PCRE2_NOTEMPTY_ATSTART
 
-       This  is like PCRE2_NOTEMPTY, except that an empty string match that is
-       not at the start of  the  subject  is  permitted.  If  the  pattern  is
-       anchored, such a match can occur only if the pattern contains \K.
+       This  is  like PCRE2_NOTEMPTY, except that it locks out an empty string
+       match only at the first matching position, that is, at the start of the
+       subject  plus  the  starting offset. An empty string match later in the
+       subject is permitted.  If the pattern is anchored,  such  a  match  can
+       occur only if the pattern contains \K.
 
          PCRE2_NO_UTF_CHECK
 
@@ -1910,9 +1909,9 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
        happens  when  PCRE2_PARTIAL_SOFT  (but not PCRE2_PARTIAL_HARD) is set,
        matching continues by testing any remaining alternatives.  Only  if  no
        complete  match can be found is PCRE2_ERROR_PARTIAL returned instead of
-       PCRE2_ERROR_NOMATCH. In other words, PCRE2_PARTIAL_SOFT says  that  the
-       caller  is  prepared to handle a partial match, but only if no complete
-       match can be found.
+       PCRE2_ERROR_NOMATCH. In other words, PCRE2_PARTIAL_SOFT specifies  that
+       the  caller  is prepared to handle a partial match, but only if no com-
+       plete match can be found.
 
        If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In  this
        case,  if  a  partial match is found, pcre2_match() immediately returns
@@ -1930,15 +1929,15 @@ NEWLINE HANDLING WHEN MATCHING
        ally the standard convention for the operating system. The default  can
        be  overridden  in  a  compile  context.   During matching, the newline
        choice affects  the  behaviour  of  the  dot,  circumflex,  and  dollar
-       metacharacters.  It  may  also  alter  the  way  the  match position is
-       advanced after a match failure for an unanchored pattern.
+       metacharacters.  It  may also alter the way the match starting position
+       is advanced after a match failure for an unanchored pattern.
 
        When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is
-       set,  and a match attempt for an unanchored pattern fails when the cur-
-       rent position is at a  CRLF  sequence,  and  the  pattern  contains  no
-       explicit  matches  for  CR  or  LF  characters,  the  match position is
-       advanced by two characters instead of one, in other words, to after the
-       CRLF.
+       set  as  the  newline convention, and a match attempt for an unanchored
+       pattern fails when the current starting position is at a CRLF sequence,
+       and  the  pattern contains no explicit matches for CR or LF characters,
+       the match position is advanced by two characters  instead  of  one,  in
+       other words, to after the CRLF.
 
        The above rule is a compromise that makes the most common cases work as
        expected. For example, if the pattern  is  .+A  (and  the  PCRE2_DOTALL
@@ -1950,8 +1949,8 @@ NEWLINE HANDLING WHEN MATCHING
 
        An explicit match for CR of LF is either a literal appearance of one of
        those characters in the  pattern,  or  one  of  the  \r  or  \n  escape
-       sequences.  Implicit  matches  such  as  [^X] do not count, nor does \s
-       (which includes CR and LF in the characters that it matches).
+       sequences.  Implicit  matches  such  as [^X] do not count, nor does \s,
+       even though it includes CR and LF in the characters that it matches.
 
        Notwithstanding the above, anomalous effects may still occur when  CRLF
        is a valid newline sequence and explicit \r or \n escapes appear in the
@@ -1968,102 +1967,105 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
        addition,  further  substrings  from  the  subject may be picked out by
        parenthesized parts of the pattern.  Following  the  usage  in  Jeffrey
        Friedl's  book,  this  is  called  "capturing" in what follows, and the
-       phrase "capturing subpattern" is used for a fragment of a pattern  that
-       picks out a substring.  PCRE2 supports several other kinds of parenthe-
-       sized subpattern that do not  cause  substrings  to  be  captured.  The
-       pcre2_pattern_info()  function can be used to find out how many captur-
-       ing subpatterns there are in a compiled pattern.
+       phrase "capturing subpattern" or "capturing group" is used for a  frag-
+       ment  of  a  pattern that picks out a substring. PCRE2 supports several
+       other kinds of parenthesized subpattern that do not cause substrings to
+       be  captured. The pcre2_pattern_info() function can be used to find out
+       how many capturing subpatterns there are in a compiled pattern.
 
        The overall matched string and any captured substrings are returned  to
-       the  caller via a vector of PCRE2_SIZE values, called the ovector. This
-       is contained within the match data block.  You can obtain direct access
-       to  the  ovector  by  calling  pcre2_get_ovector_pointer()  to find its
-       address, and pcre2_get_ovector_count() to find the number of  pairs  of
-       values  it contains. Alternatively, you can use the auxiliary functions
-       for accessing captured substrings by number or by name (see below).
+       the  caller via a vector of PCRE2_SIZE values. This is called the ovec-
+       tor, and is contained within the match  data  block.   You  can  obtain
+       direct  access to the ovector by calling pcre2_get_ovector_pointer() to
+       find its address, and pcre2_get_ovector_count() to find the  number  of
+       pairs  of  values it contains. Alternatively, you can use the auxiliary
+       functions for accessing captured substrings by number or by  name  (see
+       below).
 
        Within the ovector, the first in each pair of values is set to the off-
        set of the first code unit of a substring, and the second is set to the
-       offset of the first code unit after the end of a substring. These  val-
-       ues  are always code unit offsets, not character offsets. That is, they
-       are byte offsets in the 8-bit library, 16-bit  offsets  in  the  16-bit
+       offset  of the first code unit after the end of a substring. These val-
+       ues are always code unit offsets, not character offsets. That is,  they
+       are  byte  offsets  in  the 8-bit library, 16-bit offsets in the 16-bit
        library, and 32-bit offsets in the 32-bit library.
 
-       The  first pair of offsets (that is, ovector[0] and ovector[1]) identi-
-       fies the portion of the subject string that was matched by  the  entire
-       pattern.  The next pair is used for the first capturing subpattern, and
-       so on.  The value returned by pcre2_match() is one more than the  high-
-       est  numbered  pair  that  has been set. For example, if two substrings
-       have been captured, the returned value is 3. If there are no  capturing
-       subpatterns,  the return value from a successful match is 1, indicating
+       The first pair of offsets (that is, ovector[0] and ovector[1])  identi-
+       fies  the  portion of the subject string that was matched by the entire
+       pattern. The next pair is used for the first capturing subpattern,  and
+       so  on.  The value returned by pcre2_match() is one more than the high-
+       est numbered pair that has been set. For  example,  if  two  substrings
+       have  been captured, the returned value is 3. If there are no capturing
+       subpatterns, the return value from a successful match is 1,  indicating
        that just the first pair of offsets has been set.
 
-       If a capturing subpattern is matched repeatedly within a  single  match
+       If  a  capturing subpattern is matched repeatedly within a single match
        operation, it is the last portion of the string that it matched that is
        returned.
 
        If the ovector is too small to hold all the captured substring offsets,
-       as  much  as possible is filled in, and the function returns a value of
-       zero. If captured substrings are not of interest, pcre2_match() may  be
+       as much as possible is filled in, and the function returns a  value  of
+       zero.  If captured substrings are not of interest, pcre2_match() may be
        called with a match data block whose ovector is of minimum length (that
        is, one pair). However, if the pattern contains back references and the
        ovector is not big enough to remember the related substrings, PCRE2 has
-       to get additional memory for use during matching. Thus  it  is  usually
+       to  get  additional  memory for use during matching. Thus it is usually
        advisable to set up a match data block containing an ovector of reason-
        able size.
 
-       It is possible for capturing subpattern number n+1 to match  some  part
+       It  is  possible for capturing subpattern number n+1 to match some part
        of the subject when subpattern n has not been used at all. For example,
-       if the string "abc" is matched  against  the  pattern  (a|(z))(bc)  the
+       if  the  string  "abc"  is  matched against the pattern (a|(z))(bc) the
        return from the function is 4, and subpatterns 1 and 3 are matched, but
-       2 is not. When this happens, both values in  the  offset  pairs  corre-
+       2  is  not.  When  this happens, both values in the offset pairs corre-
        sponding to unused subpatterns are set to PCRE2_UNSET.
 
-       Offset  values  that correspond to unused subpatterns at the end of the
-       expression are also set to PCRE2_UNSET.  For  example,  if  the  string
+       Offset values that correspond to unused subpatterns at the end  of  the
+       expression  are  also  set  to  PCRE2_UNSET. For example, if the string
        "abc" is matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3
-       are not matched.  The return from the function is 2, because the  high-
+       are  not matched.  The return from the function is 2, because the high-
        est used capturing subpattern number is 1. The offsets for for the sec-
-       ond and third capturing  subpatterns  (assuming  the  vector  is  large
+       ond  and  third  capturing  subpatterns  (assuming  the vector is large
        enough, of course) are set to PCRE2_UNSET.
 
        Elements in the ovector that do not correspond to capturing parentheses
        in the pattern are never changed. That is, if a pattern contains n cap-
        turing parentheses, no more than ovector[0] to ovector[2n+1] are set by
-       pcre2_match(). The other elements retain whatever  values  they  previ-
+       pcre2_match().  The  other  elements retain whatever values they previ-
        ously had.
 
-   Other information about the match
+
+OTHER INFORMATION ABOUT A MATCH
 
        PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data);
 
        PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data);
 
-       In  addition  to  the offsets in the ovector, other information about a
-       match is retained in the match data block and can be retrieved  by  the
-       above functions.
+       As well as the offsets in the ovector, other information about a  match
+       is  retained  in the match data block and can be retrieved by the above
+       functions.
 
-       When  a  (*MARK)  name is to be passed back, pcre2_get_mark() returns a
-       pointer to the zero-terminated name, which is within the compiled  pat-
-       tern.   Otherwise  NULL  is  returned.  A (*MARK) name may be available
-       after a failed match or a partial match, as well as after a  successful
+       When a (*MARK) name is to be passed back,  pcre2_get_mark()  returns  a
+       pointer  to the zero-terminated name, which is within the compiled pat-
+       tern.  Otherwise NULL is returned. A  (*MARK)  name  may  be  available
+       after  a failed match or a partial match, as well as after a successful
        one.
 
-       The  code  unit  offset  of  the  character at which a successful match
-       started is returned by pcre2_get_startchar(). For a non-partial  match,
-       this  can  be  different to the value of ovector[0] if the pattern con-
-       tains the \K escape sequence. After  a  partial  match,  however,  this
-       value  is  always the same as ovector[0] because \K does not affect the
+       The code unit offset of the  character  at  which  a  successful  match
+       started  is returned by pcre2_get_startchar(). For a non-partial match,
+       this can be different to the value of ovector[0] if  the  pattern  con-
+       tains  the  \K  escape  sequence.  After a partial match, however, this
+       value is always the same as ovector[0] because \K does not  affect  the
        result of a partial match.
 
-   Error return values from pcre2_match()
 
-       If pcre2_match() fails, it returns a negative number. This can be  con-
-       verted  to a text string by calling pcre2_get_error_message(). Negative
-       error codes are also returned by other functions,  and  are  documented
+ERROR RETURNS FROM pcre2_match()
+
+       If  pcre2_match() fails, it returns a negative number. This can be con-
+       verted to a text string by calling pcre2_get_error_message().  Negative
+       error  codes  are  also returned by other functions, and are documented
        with them.  The codes are given names in the header file. If UTF check-
        ing is in force and an invalid UTF subject string is detected, one of a
-       number  of  UTF-specific  negative error codes is returned. Details are
+       number of UTF-specific negative error codes is  returned.  Details  are
        given in the pcre2unicode page. The following are the other errors that
        may be returned by pcre2_match():
 
@@ -2073,24 +2075,24 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
 
          PCRE2_ERROR_PARTIAL
 
-       The  subject  string did not match, but it did match partially. See the
+       The subject string did not match, but it did match partially.  See  the
        pcre2partial documentation for details of partial matching.
 
          PCRE2_ERROR_BADMAGIC
 
        PCRE2 stores a 4-byte "magic number" at the start of the compiled code,
-       to  catch  the case when it is passed a junk pointer. This is the error
+       to catch the case when it is passed a junk pointer. This is  the  error
        that is returned when the magic number is not present.
 
          PCRE2_ERROR_BADMODE
 
-       This error is given when a pattern  that  was  compiled  by  the  8-bit
-       library  is  passed  to  a  16-bit  or 32-bit library function, or vice
+       This  error  is  given  when  a  pattern that was compiled by the 8-bit
+       library is passed to a 16-bit  or  32-bit  library  function,  or  vice
        versa.
 
          PCRE2_ERROR_BADOFFSET
 
-       The value of startoffset greater than the length of the subject.
+       The value of startoffset was greater than the length of the subject.
 
          PCRE2_ERROR_BADOPTION
 
@@ -2099,35 +2101,35 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
          PCRE2_ERROR_BADUTFOFFSET
 
        The UTF code unit sequence that was passed as a subject was checked and
-       found  to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the
-       value of startoffset did not point to the beginning of a UTF  character
+       found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but  the
+       value  of startoffset did not point to the beginning of a UTF character
        or the end of the subject.
 
          PCRE2_ERROR_CALLOUT
 
-       This  error  is never generated by pcre2_match() itself. It is provided
+       This error is never generated by pcre2_match() itself. It  is  provided
        for use by callout functions that want to cause pcre2_match() to return
-       a  distinctive  error  code.  See  the  pcre2callout  documentation for
+       a distinctive  error  code.  See  the  pcre2callout  documentation  for
        details.
 
          PCRE2_ERROR_INTERNAL
 
-       An unexpected internal error has occurred. This error could  be  caused
+       An  unexpected  internal error has occurred. This error could be caused
        by a bug in PCRE2 or by overwriting of the compiled pattern.
 
          PCRE2_ERROR_JIT_BADOPTION
 
-       This  error  is  returned  when a pattern that was successfully studied
-       using JIT is being matched, but the matching mode (partial or  complete
-       match)  does  not  correspond to any JIT compilation mode. When the JIT
-       fast path function is used, this error may be also  given  for  invalid
+       This error is returned when a pattern  that  was  successfully  studied
+       using  JIT is being matched, but the matching mode (partial or complete
+       match) does not correspond to any JIT compilation mode.  When  the  JIT
+       fast  path  function  is used, this error may be also given for invalid
        options. See the pcre2jit documentation for more details.
 
          PCRE2_ERROR_JIT_STACKLIMIT
 
-       This  error  is  returned  when a pattern that was successfully studied
-       using JIT is being matched, but the memory available for  the  just-in-
-       time  processing stack is not large enough. See the pcre2jit documenta-
+       This error is returned when a pattern  that  was  successfully  studied
+       using  JIT  is being matched, but the memory available for the just-in-
+       time processing stack is not large enough. See the pcre2jit  documenta-
        tion for more details.
 
          PCRE2_ERROR_MATCHLIMIT
@@ -2136,10 +2138,10 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
 
          PCRE2_ERROR_NOMEMORY
 
-       If a pattern contains back references,  but  the  ovector  is  not  big
-       enough  to  remember  the  referenced substrings, PCRE2 gets a block of
+       If  a  pattern  contains  back  references,  but the ovector is not big
+       enough to remember the referenced substrings, PCRE2  gets  a  block  of
        memory at the start of matching to use for this purpose. There are some
-       other  special cases where extra memory is needed during matching. This
+       other special cases where extra memory is needed during matching.  This
        error is given when memory cannot be obtained.
 
          PCRE2_ERROR_NULL
@@ -2148,13 +2150,13 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
 
          PCRE2_ERROR_RECURSELOOP
 
-       This error is returned when  pcre2_match()  detects  a  recursion  loop
-       within  the  pattern. Specifically, it means that either the whole pat-
+       This  error  is  returned  when  pcre2_match() detects a recursion loop
+       within the pattern. Specifically, it means that either the  whole  pat-
        tern or a subpattern has been called recursively for the second time at
-       the  same  position  in  the  subject string. Some simple patterns that
-       might do this are detected and faulted at compile time, but  more  com-
-       plicated  cases,  in particular mutual recursions between two different
-       subpatterns, cannot be detected until run time.
+       the same position in the subject  string.  Some  simple  patterns  that
+       might  do  this are detected and faulted at compile time, but more com-
+       plicated cases, in particular mutual recursions between  two  different
+       subpatterns, cannot be detected until matching is attempted.
 
          PCRE2_ERROR_RECURSIONLIMIT
 
@@ -2176,52 +2178,52 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
 
        void pcre2_substring_free(PCRE2_UCHAR *buffer);
 
-       Captured substrings can be accessed directly by using  the  ovector  as
+       Captured  substrings  can  be accessed directly by using the ovector as
        described above.  For convenience, auxiliary functions are provided for
-       extracting  captured  substrings  as  new,  separate,   zero-terminated
-       strings.  The  functions in this section identify substrings by number.
-       The next section describes similar functions for extracting  substrings
+       extracting   captured  substrings  as  new,  separate,  zero-terminated
+       strings. The functions in this section identify substrings  by  number.
+       The  next section describes similar functions for extracting substrings
        by name. A substring that contains a binary zero is correctly extracted
-       and has a further zero added on the end, but  the  result  is  not,  of
+       and  has  a  further  zero  added on the end, but the result is not, of
        course, a C string.
 
-       You  can  find the length in code units of a captured substring without
-       extracting it by calling pcre2_substring_length_bynumber().  The  first
-       argument  is a pointer to the match data block, the second is the group
-       number, and the third is a pointer to a variable into which the  length
+       You can find the length in code units of a captured  substring  without
+       extracting  it  by calling pcre2_substring_length_bynumber(). The first
+       argument is a pointer to the match data block, the second is the  group
+       number,  and the third is a pointer to a variable into which the length
        is placed.
 
-       The  pcre2_substring_copy_bynumber()  function copies one string into a
-       supplied buffer, whereas pcre2_substring_get_bynumber() copies it  into
+       The pcre2_substring_copy_bynumber() function copies one string  into  a
+       supplied  buffer, whereas pcre2_substring_get_bynumber() copies it into
        new memory, obtained using the same memory allocation function that was
-       used for the match data block. The first two arguments of  these  func-
-       tions  are a pointer to the match data block and a capturing group num-
-       ber. A group number of zero extracts the  substring  that  matched  the
+       used  for  the match data block. The first two arguments of these func-
+       tions are a pointer to the match data block and a capturing group  num-
+       ber.  A  group  number  of zero extracts the substring that matched the
        entire pattern, and higher values extract the captured substrings.
 
        The final arguments of pcre2_substring_copy_bynumber() are a pointer to
        the buffer and a pointer to a variable that contains its length in code
-       units.   This  is  updated  to  contain the actual number of code units
-       used, excluding the terminating zero.
+       units.  This is updated to contain the actual number of code units used
+       for the extracted substring, excluding the terminating zero.
 
        For pcre2_substring_get_bynumber() the third and fourth arguments point
-       to  variables that are updated with a pointer to the new memory and the
-       number of code units that comprise the substring, again  excluding  the
-       terminating  zero.  When  the substring is no longer needed, the memory
+       to variables that are updated with a pointer to the new memory and  the
+       number  of  code units that comprise the substring, again excluding the
+       terminating zero. When the substring is no longer  needed,  the  memory
        should be freed by calling pcre2_substring_free().
 
-       The return value from these functions is zero for success,  or  one  of
+       The  return  value  from these functions is zero for success, or one of
        these error codes:
 
          PCRE2_ERROR_NOMEMORY
 
-       The  buffer  was  too small for pcre2_substring_copy_bynumber(), or the
+       The buffer was too small for  pcre2_substring_copy_bynumber(),  or  the
        attempt to get memory failed for pcre2_substring_get_bynumber().
 
          PCRE2_ERROR_NOSUBSTRING
 
-       No substring with the given number was captured. This could be  because
-       there  is  no capturing group of that number in the pattern, or because
+       No  substring with the given number was captured. This could be because
+       there is no capturing group of that number in the pattern,  or  because
        the group with that number did not participate in the match, or because
        the ovector was too small to capture that group.
 
@@ -2233,28 +2235,28 @@ EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
 
        void pcre2_substring_list_free(PCRE2_SPTR *list);
 
-       The  pcre2_substring_list_get()  function  extracts  all available sub-
-       strings and builds a list of pointers to them, and a second  list  that
-       contains  their  lengths  (in code units), excluding a terminating zero
-       that is added to each of them. All this is done in a  single  block  of
-       memory  that is obtained using the same memory allocation function that
-       was used to get the match data block.
+       The pcre2_substring_list_get() function  extracts  all  available  sub-
+       strings  and  builds  a  list of pointers to them. It also (optionally)
+       builds a second list that  contains  their  lengths  (in  code  units),
+       excluding a terminating zero that is added to each of them. All this is
+       done in a single block of memory that is obtained using the same memory
+       allocation function that was used to get the match data block.
 
-       The address of the memory block is returned via listptr, which is  also
+       The  address of the memory block is returned via listptr, which is also
        the start of the list of string pointers. The end of the list is marked
-       by a NULL pointer. The address of the list of lengths is  returned  via
-       lengthsptr.  If your strings do not contain binary zeros and you do not
+       by  a  NULL pointer. The address of the list of lengths is returned via
+       lengthsptr. If your strings do not contain binary zeros and you do  not
        therefore need the lengths, you may supply NULL as the lengthsptr argu-
-       ment  to  disable  the  creation of a list of lengths. The yield of the
-       function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the  mem-
-       ory  block could not be obtained. When the list is no longer needed, it
+       ment to disable the creation of a list of lengths.  The  yield  of  the
+       function  is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem-
+       ory block could not be obtained. When the list is no longer needed,  it
        should be freed by calling pcre2_substring_list_free().
 
        If this function encounters a substring that is unset, which can happen
-       when  capturing subpattern number n+1 matches some part of the subject,
-       but subpattern n has not been used at all, it returns an empty  string.
-       This  can  be  distinguished  from  a  genuine zero-length substring by
-       inspecting the  appropriate  offset  in  the  ovector,  which  contains
+       when capturing subpattern number n+1 matches some part of the  subject,
+       but  subpattern n has not been used at all, it returns an empty string.
+       This can be distinguished  from  a  genuine  zero-length  substring  by
+       inspecting  the  appropriate  offset  in  the  ovector,  which  contain
        PCRE2_UNSET for unset substrings.
 
 
@@ -2274,26 +2276,25 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME
 
        void pcre2_substring_free(PCRE2_UCHAR *buffer);
 
-       To  extract a substring by name, you first have to find associated num-
+       To extract a substring by name, you first have to find associated  num-
        ber.  For example, for this pattern:
 
          (a+)b(?\d+)...
 
        the number of the subpattern called "xxx" is 2. If the name is known to
-       be  unique  (PCRE2_DUPNAMES  was not set), you can find the number from
+       be unique (PCRE2_DUPNAMES was not set), you can find  the  number  from
        the name by calling pcre2_substring_number_from_name(). The first argu-
-       ment  is the compiled pattern, and the second is the name. The yield of
+       ment is the compiled pattern, and the second is the name. The yield  of
        the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there
-       is  no  subpattern  of  that  name, or PCRE2_ERROR_NOUNIQUESUBSTRING if
+       is no subpattern of  that  name,  or  PCRE2_ERROR_NOUNIQUESUBSTRING  if
        there is more than one subpattern of that name.
 
        Given the number, you can extract the substring directly, or use one of
-       the functions described in the previous section. For convenience, there
-       are also "byname" functions that correspond  to  the  "bynumber"  func-
-       tions,  the  only  difference  being that the second argument is a name
-       instead of a number.  However, if PCRE2_DUPNAMES is set and  there  are
-       duplicate  names,  the behaviour may not be what you want (see the next
-       section).
+       the functions described above. For convenience, there are also "byname"
+       functions that correspond to the "bynumber" functions, the only differ-
+       ence being that the second argument is a name instead of a number. How-
+       ever,  if  PCRE2_DUPNAMES is set and there are duplicate names, the be-
+       haviour may not be what you want.
 
        Warning: If the pattern uses the (?| feature to set up multiple subpat-
        terns  with  the  same number, as described in the section on duplicate
@@ -2331,8 +2332,8 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        brackets are required only if the following character would  be  inter-
        preted as part of the number or name. The number may be zero to include
        the entire matched string.   For  example,  if  the  pattern  a(b)c  is
-       matched  with "[abc]" and the replacement string "+$1$0$1+", the result
-       is "[+babcb+]". Group insertion is done by calling  pcre2_copy_byname()
+       matched  with "=abc=" and the replacement string "+$1$0$1+", the result
+       is "=+babcb+=". Group insertion is done by calling  pcre2_copy_byname()
        or pcre2_copy_bynumber() as appropriate.
 
        The  first  seven  arguments  of pcre2_substitute() are the same as for
@@ -2382,40 +2383,41 @@ DUPLICATE SUBPATTERN NAMES
        pcre2_substring_get_byname()  return  the first substring corresponding
        to the given name that is set. If none are set, PCRE2_ERROR_NOSUBSTRING
        is  returned.  The  pcre2_substring_number_from_name() function returns
-       one of the numbers that are associated with the name,  but  it  is  not
-       defined which it is.
+       the error PCRE2_ERROR_NOUNIQUESUBSTRING.
 
-       If  you want to get full details of all captured substrings for a given
-       name, you must use the pcre2_substring_nametable_scan()  function.  The
-       first  argument is the compiled pattern, and the second is the name. If
-       the third and fourth arguments are NULL, the function returns  a  group
-       number (it is not defined which). Otherwise, the third and fourth argu-
-       ments must be pointers to variables that are updated by  the  function.
-       After it has run, they point to the first and last entries in the name-
-       to-number table for the given name, and the function returns the length
-       of  each  entry.  In both cases, PCRE2_ERROR_NOSUBSTRING is returned if
-       there are no entries for the given name.
+       If you want to get full details of all captured substrings for a  given
+       name,  you  must use the pcre2_substring_nametable_scan() function. The
+       first argument is the compiled pattern, and the second is the name.  If
+       the  third  and fourth arguments are NULL, the function returns a group
+       number for a unique name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise.
+
+       When the third and fourth arguments are not NULL, they must be pointers
+       to  variables  that are updated by the function. After it has run, they
+       point to the first and last entries in the name-to-number table for the
+       given  name,  and the function returns the length of each entry in code
+       units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there  are
+       no entries for the given name.
 
        The format of the name table is described above in the section entitled
-       Information  about a pattern above.  Given all the relevant entries for
+       Information about a pattern above.  Given all the relevant entries  for
        the name, you can extract each of their numbers, and hence the captured
        data.
 
 
-FINDING ALL POSSIBLE MATCHES
+FINDING ALL POSSIBLE MATCHES AT ONE POSITION
 
-       The  traditional  matching  function  uses a similar algorithm to Perl,
-       which stops when it finds the first match, starting at a given point in
-       the  subject.  If you want to find all possible matches, or the longest
-       possible match at a given  position,  consider  using  the  alternative
-       matching  function (see below) instead.  If you cannot use the alterna-
-       tive function, you can kludge it up by making use of the callout facil-
-       ity, which is described in the pcre2callout documentation.
+       The traditional matching function uses a  similar  algorithm  to  Perl,
+       which  stops when it finds the first match at a given point in the sub-
+       ject. If you want to find all possible matches, or the longest possible
+       match  at  a  given  position,  consider using the alternative matching
+       function (see below) instead. If you cannot use the  alternative  func-
+       tion, you can kludge it up by making use of the callout facility, which
+       is described in the pcre2callout documentation.
 
        What you have to do is to insert a callout right at the end of the pat-
-       tern.  When your callout function is called, extract and save the  cur-
-       rent  matched  substring.  Then return 1, which forces pcre2_match() to
-       backtrack and try other alternatives. Ultimately, when it runs  out  of
+       tern.   When your callout function is called, extract and save the cur-
+       rent matched substring. Then return 1, which  forces  pcre2_match()  to
+       backtrack  and  try other alternatives. Ultimately, when it runs out of
        matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH.
 
 
@@ -2427,26 +2429,26 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
          pcre2_match_context *mcontext,
          int *workspace, PCRE2_SIZE wscount);
 
-       The  function  pcre2_dfa_match()  is  called  to match a subject string
-       against a compiled pattern, using a matching algorithm that  scans  the
-       subject  string  just  once, and does not backtrack. This has different
-       characteristics to the normal algorithm, and  is  not  compatible  with
-       Perl.  Some of the features of PCRE2 patterns are not supported. Never-
-       theless, there are times when this kind of matching can be useful.  For
-       a  discussion  of  the  two matching algorithms, and a list of features
+       The function pcre2_dfa_match() is called  to  match  a  subject  string
+       against  a  compiled pattern, using a matching algorithm that scans the
+       subject string just once, and does not backtrack.  This  has  different
+       characteristics  to  the  normal  algorithm, and is not compatible with
+       Perl. Some of the features of PCRE2 patterns are not supported.  Never-
+       theless,  there are times when this kind of matching can be useful. For
+       a discussion of the two matching algorithms, and  a  list  of  features
        that pcre2_dfa_match() does not support, see the pcre2matching documen-
        tation.
 
-       The  arguments  for  the pcre2_dfa_match() function are the same as for
+       The arguments for the pcre2_dfa_match() function are the  same  as  for
        pcre2_match(), plus two extras. The ovector within the match data block
        is used in a different way, and this is described below. The other com-
-       mon arguments are used in the same way as for pcre2_match(),  so  their
+       mon  arguments  are used in the same way as for pcre2_match(), so their
        description is not repeated here.
 
-       The  two  additional  arguments provide workspace for the function. The
-       workspace vector should contain at least 20 elements. It  is  used  for
+       The two additional arguments provide workspace for  the  function.  The
+       workspace  vector  should  contain at least 20 elements. It is used for
        keeping  track  of  multiple  paths  through  the  pattern  tree.  More
-       workspace is needed for patterns and subjects where there are a lot  of
+       workspace  is needed for patterns and subjects where there are a lot of
        potential matches.
 
        Here is an example of a simple call to pcre2_dfa_match():
@@ -2466,45 +2468,45 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
 
    Option bits for pcre_dfa_match()
 
-       The  unused  bits of the options argument for pcre2_dfa_match() must be
-       zero. The only bits that may be set are  PCRE2_ANCHORED,  PCRE2_NOTBOL,
+       The unused bits of the options argument for pcre2_dfa_match()  must  be
+       zero.  The  only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL,
        PCRE2_NOTEOL,          PCRE2_NOTEMPTY,          PCRE2_NOTEMPTY_ATSTART,
        PCRE2_NO_UTF_CHECK,       PCRE2_PARTIAL_HARD,       PCRE2_PARTIAL_SOFT,
-       PCRE2_DFA_SHORTEST,  and  PCRE2_DFA_RESTART.  All  but the last four of
-       these are exactly the same as for pcre2_match(), so  their  description
+       PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but  the  last  four  of
+       these  are  exactly the same as for pcre2_match(), so their description
        is not repeated here.
 
          PCRE2_PARTIAL_HARD
          PCRE2_PARTIAL_SOFT
 
-       These  have  the  same general effect as they do for pcre2_match(), but
-       the details are slightly different. When PCRE2_PARTIAL_HARD is set  for
-       pcre2_dfa_match(),  it  returns  PCRE2_ERROR_PARTIAL  if the end of the
+       These have the same general effect as they do  for  pcre2_match(),  but
+       the  details are slightly different. When PCRE2_PARTIAL_HARD is set for
+       pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if  the  end  of  the
        subject is reached and there is still at least one matching possibility
        that requires additional characters. This happens even if some complete
-       matches have already been found. When PCRE2_PARTIAL_SOFT  is  set,  the
-       return  code  PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL
-       if the end of the subject is  reached,  there  have  been  no  complete
+       matches  have  already  been found. When PCRE2_PARTIAL_SOFT is set, the
+       return code PCRE2_ERROR_NOMATCH is converted  into  PCRE2_ERROR_PARTIAL
+       if  the  end  of  the  subject  is reached, there have been no complete
        matches, but there is still at least one matching possibility. The por-
-       tion of the string that was inspected when the  longest  partial  match
+       tion  of  the  string that was inspected when the longest partial match
        was found is set as the first matching string in both cases. There is a
-       more detailed discussion of partial and  multi-segment  matching,  with
+       more  detailed  discussion  of partial and multi-segment matching, with
        examples, in the pcre2partial documentation.
 
          PCRE2_DFA_SHORTEST
 
-       Setting  the PCRE2_DFA_SHORTEST option causes the matching algorithm to
+       Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm  to
        stop as soon as it has found one match. Because of the way the alterna-
-       tive  algorithm  works, this is necessarily the shortest possible match
+       tive algorithm works, this is necessarily the shortest  possible  match
        at the first possible matching point in the subject string.
 
          PCRE2_DFA_RESTART
 
-       When pcre2_dfa_match() returns a partial match, it is possible to  call
+       When  pcre2_dfa_match() returns a partial match, it is possible to call
        it again, with additional subject characters, and have it continue with
        the same match. The PCRE2_DFA_RESTART option requests this action; when
-       it  is  set,  the workspace and wscount options must reference the same
-       vector as before because data about the match so far is  left  in  them
+       it is set, the workspace and wscount options must  reference  the  same
+       vector  as  before  because data about the match so far is left in them
        after a partial match. There is more discussion of this facility in the
        pcre2partial documentation.
 
@@ -2512,8 +2514,8 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
 
        When pcre2_dfa_match() succeeds, it may have matched more than one sub-
        string in the subject. Note, however, that all the matches from one run
-       of the function start at the same point in  the  subject.  The  shorter
-       matches  are all initial substrings of the longer matches. For example,
+       of  the  function  start  at the same point in the subject. The shorter
+       matches are all initial substrings of the longer matches. For  example,
        if the pattern
 
          <.*>
@@ -2528,22 +2530,21 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
           
            
 
-       On success, the yield of the function is a number  greater  than  zero,
-       which  is  the  number  of  matched substrings. The offsets of the sub-
-       strings are returned in the ovector, and can be extracted in  the  same
-       way  as  for  pcre2_match().   They  are  returned  in reverse order of
-       length; that is, the longest matching string is given first.  If  there
-       were  too  many matches to fit into the ovector, the yield of the func-
+       On  success,  the  yield of the function is a number greater than zero,
+       which is the number of matched substrings.  The  offsets  of  the  sub-
+       strings  are  returned in the ovector, and can be extracted in the same
+       way as for pcre2_match().   They  are  returned  in  reverse  order  of
+       length;  that  is, the longest matching string is given first. If there
+       were too many matches to fit into the ovector, the yield of  the  func-
        tion is zero, and the vector is filled with the longest matches.
 
-       NOTE: PCRE2's "auto-possessification" optimization usually  applies  to
-       character  repeats at the end of a pattern (as well as internally). For
-       example, the pattern "a\d+" is compiled as if it were  "a\d++"  because
-       there  is  no  point  in backtracking into the repeated digits. For DFA
+       NOTE:  PCRE2's  "auto-possessification" optimization usually applies to
+       character repeats at the end of a pattern (as well as internally).  For
+       example,  the pattern "a\d+" is compiled as if it were "a\d++". For DFA
        matching, this means that only one possible  match  is  found.  If  you
        really  do  want multiple matches in such cases, either use an ungreedy
-       repeat ("a\d+?") or set the PCRE2_NO_AUTO_POSSESS option  when  compil-
-       ing.
+       repeat auch as "a\d+?" or set  the  PCRE2_NO_AUTO_POSSESS  option  when
+       compiling.
 
    Error returns from pcre2_dfa_match()
 
@@ -2578,7 +2579,7 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
 
          PCRE2_ERROR_DFA_BADRESTART
 
-       When pcre2_dfa_match() is called  with  the  pcre2_dfa_RESTART  option,
+       When pcre2_dfa_match() is called  with  the  PCRE2_DFA_RESTART  option,
        some  plausibility  checks  are  made on the contents of the workspace,
        which should contain data about the previous partial match. If  any  of
        these checks fail, this error is given.
@@ -2586,21 +2587,21 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
 
 SEE ALSO
 
-       pcre2build(3),    pcre2libs(3),    pcre2callout(3),   pcre2matching(3),
-       pcre2partial(3),    pcre2posix(3),    pcre2demo(3),     pcre2sample(3),
-       pcre2stack(3).
+       pcre2build(3),    pcre2callout(3),    pcre2demo(3),   pcre2matching(3),
+       pcre2partial(3),    pcre2posix(3),    pcre2sample(3),    pcre2stack(3),
+       pcre2unicode(3).
 
 
 AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
 
-       Last updated: 11 November 2014
+       Last updated: 21 November 2014
        Copyright (c) 1997-2014 University of Cambridge.
 ------------------------------------------------------------------------------
 
@@ -3043,7 +3044,7 @@ AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
@@ -3279,7 +3280,7 @@ AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
@@ -3465,7 +3466,7 @@ AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
@@ -3849,7 +3850,7 @@ AUTHOR
 
        Philip Hazel (FAQ by Zoltan Herczeg)
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
@@ -3917,7 +3918,7 @@ AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
@@ -4136,7 +4137,7 @@ AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
@@ -4576,7 +4577,7 @@ AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
@@ -4801,7 +4802,7 @@ AUTHOR
 
        Philip Hazel
        University Computing Service
-       Cambridge CB2 3QH, England.
+       Cambridge, England.
 
 
 REVISION
diff --git a/doc/pcre2api.3 b/doc/pcre2api.3
index 08fd9cc..81bfe23 100644
--- a/doc/pcre2api.3
+++ b/doc/pcre2api.3
@@ -1,4 +1,4 @@
-.TH PCRE2API 3 "18 November 2014" "PCRE2 10.00"
+.TH PCRE2API 3 "21 November 2014" "PCRE2 10.00"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .sp
@@ -674,7 +674,7 @@ patterns that are not anchored, the count restarts from zero for each position
 in the subject string. This limit is not relevant to \fBpcre2_dfa_match()\fP,
 which ignores it.
 .P
-When \fBpcre2_match()\fP is called with a pattern that was successfully 
+When \fBpcre2_match()\fP is called with a pattern that was successfully
 processed by \fBpcre2_jit_compile()\fP, the way in which matching is executed
 is entirely different. However, there is still the possibility of runaway
 matching that goes on for a very long time, and so the \fImatch_limit\fP value
@@ -740,7 +740,7 @@ documentation. See the
 .\" HREF
 \fBpcre2build\fP
 .\"
-documentation for details of how to build PCRE2. 
+documentation for details of how to build PCRE2.
 .P
 Using the heap for recursion is a non-standard way of building PCRE2, for use
 in environments that have limited stacks. Because of the greater use of memory
@@ -904,7 +904,7 @@ PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of memory that
 contains the compiled pattern and related data. The caller must free the memory
 by calling \fBpcre2_code_free()\fP when it is no longer needed.
 .P
-If the compile context argument \fIccontext\fP is NULL, memory for the compiled 
+If the compile context argument \fIccontext\fP is NULL, memory for the compiled
 pattern is obtained by calling \fBmalloc()\fP. Otherwise, it is obtained from
 the same memory function that was used for the compile context.
 .P
@@ -1569,15 +1569,17 @@ values.
 .P
 The map consists of a number of fixed-size entries. PCRE2_INFO_NAMECOUNT gives
 the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives the size of each
-entry; both of these return a \fBuint32_t\fP value. The entry size depends on
-the length of the longest name. PCRE2_INFO_NAMETABLE returns a pointer to the
-first entry of the table. This is a PCRE2_SPTR pointer to a block of code
-units. In the 8-bit library, the first two bytes of each entry are the number
-of the capturing parenthesis, most significant byte first. In the 16-bit
-library, the pointer points to 16-bit data units, the first of which contains
-the parenthesis number. In the 32-bit library, the pointer points to 32-bit
-data units, the first of which contains the parenthesis number. The rest of the
-entry is the corresponding name, zero terminated.
+entry in code units; both of these return a \fBuint32_t\fP value. The entry
+size depends on the length of the longest name.
+.P
+PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table. This is
+a PCRE2_SPTR pointer to a block of code units. In the 8-bit library, the first
+two bytes of each entry are the number of the capturing parenthesis, most
+significant byte first. In the 16-bit library, the pointer points to 16-bit
+code units, the first of which contains the parenthesis number. In the 32-bit
+library, the pointer points to 32-bit code units, the first of which contains
+the parenthesis number. The rest of the entry is the corresponding name, zero
+terminated.
 .P
 The names are in alphabetical order. If (?| is used to create multiple groups
 with the same number, as described in the
@@ -1621,14 +1623,14 @@ different for each compiled pattern.
 .sp
   PCRE2_INFO_NEWLINE
 .sp
-The output is a \fBuint32_t\fP with one of the following values: 
+The output is a \fBuint32_t\fP with one of the following values:
 .sp
   PCRE2_NEWLINE_CR       Carriage return (CR)
   PCRE2_NEWLINE_LF       Linefeed (LF)
   PCRE2_NEWLINE_CRLF     Carriage return, linefeed (CRLF)
   PCRE2_NEWLINE_ANY      Any Unicode line ending
   PCRE2_NEWLINE_ANYCRLF  Any of CR, LF, or CRLF
-.sp  
+.sp
 This specifies the default character sequence that will be recognized as
 meaning "newline" while matching.
 .sp
@@ -1670,7 +1672,7 @@ particular, the match data block contains a vector of offsets into the subject
 string that define the matched part of the subject and any substrings that were
 captured. This is know as the \fIovector\fP.
 .P
-Before calling \fBpcre2_match()\fP, \fBpcre2_dfa_match()\fP, or 
+Before calling \fBpcre2_match()\fP, \fBpcre2_dfa_match()\fP, or
 \fBpcre2_jit_match()\fP you must create a match data block by calling one of
 the creation functions above. For \fBpcre2_match_data_create()\fP, the first
 argument is the number of pairs of offsets in the \fIovector\fP. One pair of
@@ -1820,7 +1822,7 @@ PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their action is described below.
 .P
 Setting PCRE2_ANCHORED at match time is not supported by the just-in-time (JIT)
 compiler. If it is set, JIT matching is disabled and the normal interpretive
-code in \fBpcre2_match()\fP is run. The remaining options are supported for JIT 
+code in \fBpcre2_match()\fP is run. The remaining options are supported for JIT
 matching.
 .sp
   PCRE2_ANCHORED
@@ -1835,17 +1837,18 @@ matching.
 .sp
 This option specifies that first character of the subject string is not the
 beginning of a line, so the circumflex metacharacter should not match before
-it. Setting this without PCRE2_MULTILINE (at compile time) causes circumflex
-never to match. This option affects only the behaviour of the circumflex
-metacharacter. It does not affect \eA.
+it. Setting this without having set PCRE2_MULTILINE at compile time causes
+circumflex never to match. This option affects only the behaviour of the
+circumflex metacharacter. It does not affect \eA.
 .sp
   PCRE2_NOTEOL
 .sp
 This option specifies that the end of the subject string is not the end of a
 line, so the dollar metacharacter should not match it nor (except in multiline
-mode) a newline immediately before it. Setting this without PCRE2_MULTILINE (at
-compile time) causes dollar never to match. This option affects only the
-behaviour of the dollar metacharacter. It does not affect \eZ or \ez.
+mode) a newline immediately before it. Setting this without having set
+PCRE2_MULTILINE at compile time causes dollar never to match. This option
+affects only the behaviour of the dollar metacharacter. It does not affect \eZ
+or \ez.
 .sp
   PCRE2_NOTEMPTY
 .sp
@@ -1857,13 +1860,16 @@ match the empty string, the entire match fails. For example, if the pattern
 .sp
 is applied to a string not beginning with "a" or "b", it matches an empty
 string at the start of the subject. With PCRE2_NOTEMPTY set, this match is not
-valid, so PCRE2 searches further into the string for occurrences of "a" or "b".
+valid, so \fBpcre2_match()\fP searches further into the string for occurrences
+of "a" or "b".
 .sp
   PCRE2_NOTEMPTY_ATSTART
 .sp
-This is like PCRE2_NOTEMPTY, except that an empty string match that is not at
-the start of the subject is permitted. If the pattern is anchored, such a match
-can occur only if the pattern contains \eK.
+This is like PCRE2_NOTEMPTY, except that it locks out an empty string match
+only at the first matching position, that is, at the start of the subject plus
+the starting offset. An empty string match later in the subject is permitted.
+If the pattern is anchored, such a match can occur only if the pattern contains
+\eK.
 .sp
   PCRE2_NO_UTF_CHECK
 .sp
@@ -1913,8 +1919,8 @@ subject characters to complete the match. If this happens when
 PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, matching continues by
 testing any remaining alternatives. Only if no complete match can be found is
 PCRE2_ERROR_PARTIAL returned instead of PCRE2_ERROR_NOMATCH. In other words,
-PCRE2_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
-but only if no complete match can be found.
+PCRE2_PARTIAL_SOFT specifies that the caller is prepared to handle a partial
+match, but only if no complete match can be found.
 .P
 If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this case, if
 a partial match is found, \fBpcre2_match()\fP immediately returns
@@ -1943,13 +1949,13 @@ compile context.
 .\"
 During matching, the newline choice affects the behaviour of the dot,
 circumflex, and dollar metacharacters. It may also alter the way the match
-position is advanced after a match failure for an unanchored pattern.
+starting position is advanced after a match failure for an unanchored pattern.
 .P
-When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is set,
-and a match attempt for an unanchored pattern fails when the current position
-is at a CRLF sequence, and the pattern contains no explicit matches for CR or
-LF characters, the match position is advanced by two characters instead of one,
-in other words, to after the CRLF.
+When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is set as
+the newline convention, and a match attempt for an unanchored pattern fails
+when the current starting position is at a CRLF sequence, and the pattern
+contains no explicit matches for CR or LF characters, the match position is
+advanced by two characters instead of one, in other words, to after the CRLF.
 .P
 The above rule is a compromise that makes the most common cases work as
 expected. For example, if the pattern is .+A (and the PCRE2_DOTALL option is
@@ -1960,8 +1966,8 @@ reference, and so advances only by one character after the first failure.
 .P
 An explicit match for CR of LF is either a literal appearance of one of those
 characters in the pattern, or one of the \er or \en escape sequences. Implicit
-matches such as [^X] do not count, nor does \es (which includes CR and LF in
-the characters that it matches).
+matches such as [^X] do not count, nor does \es, even though it includes CR and
+LF in the characters that it matches.
 .P
 Notwithstanding the above, anomalous effects may still occur when CRLF is a
 valid newline sequence and explicit \er or \en escapes appear in the pattern.
@@ -1981,15 +1987,15 @@ In general, a pattern matches a certain portion of the subject, and in
 addition, further substrings from the subject may be picked out by
 parenthesized parts of the pattern. Following the usage in Jeffrey Friedl's
 book, this is called "capturing" in what follows, and the phrase "capturing
-subpattern" is used for a fragment of a pattern that picks out a substring.
-PCRE2 supports several other kinds of parenthesized subpattern that do not
-cause substrings to be captured. The \fBpcre2_pattern_info()\fP function can be
-used to find out how many capturing subpatterns there are in a compiled
-pattern.
+subpattern" or "capturing group" is used for a fragment of a pattern that picks
+out a substring. PCRE2 supports several other kinds of parenthesized subpattern
+that do not cause substrings to be captured. The \fBpcre2_pattern_info()\fP
+function can be used to find out how many capturing subpatterns there are in a
+compiled pattern.
 .P
 The overall matched string and any captured substrings are returned to the
-caller via a vector of PCRE2_SIZE values, called the \fBovector\fP. This is
-contained within the
+caller via a vector of PCRE2_SIZE values. This is called the \fBovector\fP, and
+is contained within the
 .\" HTML 
 .\" 
 match data block.
@@ -2062,7 +2068,7 @@ had.
 .
 .
 .\" HTML 
-.SS "Other information about the match"
+.SH "OTHER INFORMATION ABOUT A MATCH"
 .rs
 .sp
 .nf
@@ -2071,7 +2077,7 @@ had.
 .B PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *\fImatch_data\fP);
 .fi
 .P
-In addition to the offsets in the ovector, other information about a match is
+As well as the offsets in the ovector, other information about a match is
 retained in the match data block and can be retrieved by the above functions.
 .P
 When a (*MARK) name is to be passed back, \fBpcre2_get_mark()\fP returns a
@@ -2087,7 +2093,7 @@ as \fIovector[0]\fP because \eK does not affect the result of a partial match.
 .
 .
 .\" HTML 
-.SS "Error return values from \fBpcre2_match()\fP"
+.SH "ERROR RETURNS FROM \fBpcre2_match()\fP"
 .rs
 .sp
 If \fBpcre2_match()\fP fails, it returns a negative number. This can be
@@ -2127,7 +2133,7 @@ passed to a 16-bit or 32-bit library function, or vice versa.
 .sp
   PCRE2_ERROR_BADOFFSET
 .sp
-The value of \fIstartoffset\fP greater than the length of the subject.
+The value of \fIstartoffset\fP was greater than the length of the subject.
 .sp
   PCRE2_ERROR_BADOPTION
 .sp
@@ -2200,8 +2206,8 @@ the pattern. Specifically, it means that either the whole pattern or a
 subpattern has been called recursively for the second time at the same position
 in the subject string. Some simple patterns that might do this are detected and
 faulted at compile time, but more complicated cases, in particular mutual
-recursions between two different subpatterns, cannot be detected until run
-time.
+recursions between two different subpatterns, cannot be detected until matching
+is attempted.
 .sp
   PCRE2_ERROR_RECURSIONLIMIT
 .sp
@@ -2254,8 +2260,8 @@ extract the captured substrings.
 .P
 The final arguments of \fBpcre2_substring_copy_bynumber()\fP are a pointer to
 the buffer and a pointer to a variable that contains its length in code units.
-This is updated to contain the actual number of code units used, excluding the
-terminating zero.
+This is updated to contain the actual number of code units used for the
+extracted substring, excluding the terminating zero.
 .P
 For \fBpcre2_substring_get_bynumber()\fP the third and fourth arguments point
 to variables that are updated with a pointer to the new memory and the number
@@ -2290,10 +2296,11 @@ small to capture that group.
 .fi
 .P
 The \fBpcre2_substring_list_get()\fP function extracts all available substrings
-and builds a list of pointers to them, and a second list that contains their
-lengths (in code units), excluding a terminating zero that is added to each of
-them. All this is done in a single block of memory that is obtained using the
-same memory allocation function that was used to get the match data block.
+and builds a list of pointers to them. It also (optionally) builds a second
+list that contains their lengths (in code units), excluding a terminating zero
+that is added to each of them. All this is done in a single block of memory
+that is obtained using the same memory allocation function that was used to get
+the match data block.
 .P
 The address of the memory block is returned via \fIlistptr\fP, which is also
 the start of the list of string pointers. The end of the list is marked by a
@@ -2309,7 +2316,7 @@ If this function encounters a substring that is unset, which can happen when
 capturing subpattern number \fIn+1\fP matches some part of the subject, but
 subpattern \fIn\fP has not been used at all, it returns an empty string. This
 can be distinguished from a genuine zero-length substring by inspecting the
-appropriate offset in the ovector, which contains PCRE2_UNSET for unset
+appropriate offset in the ovector, which contain PCRE2_UNSET for unset
 substrings.
 .
 .
@@ -2347,11 +2354,10 @@ name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is more than one subpattern of
 that name.
 .P
 Given the number, you can extract the substring directly, or use one of the
-functions described in the previous section. For convenience, there are also
-"byname" functions that correspond to the "bynumber" functions, the only
-difference being that the second argument is a name instead of a number.
-However, if PCRE2_DUPNAMES is set and there are duplicate names,
-the behaviour may not be what you want (see the next section).
+functions described above. For convenience, there are also "byname" functions
+that correspond to the "bynumber" functions, the only difference being that the
+second argument is a name instead of a number. However, if PCRE2_DUPNAMES is
+set and there are duplicate names, the behaviour may not be what you want.
 .P
 \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
 subpatterns with the same number, as described in the
@@ -2398,8 +2404,8 @@ recognized:
 Either a group number or a group name can be given for . Curly brackets are
 required only if the following character would be interpreted as part of the
 number or name. The number may be zero to include the entire matched string.
-For example, if the pattern a(b)c is matched with "[abc]" and the replacement
-string "+$1$0$1+", the result is "[+babcb+]". Group insertion is done by
+For example, if the pattern a(b)c is matched with "=abc=" and the replacement
+string "+$1$0$1+", the result is "=+babcb+=". Group insertion is done by
 calling \fBpcre2_copy_byname()\fP or \fBpcre2_copy_bynumber()\fP as
 appropriate.
 .P
@@ -2452,18 +2458,19 @@ documentation.
 When duplicates are present, \fBpcre2_substring_copy_byname()\fP and
 \fBpcre2_substring_get_byname()\fP return the first substring corresponding to
 the given name that is set. If none are set, PCRE2_ERROR_NOSUBSTRING is
-returned. The \fBpcre2_substring_number_from_name()\fP function returns one of
-the numbers that are associated with the name, but it is not defined which it
-is.
+returned. The \fBpcre2_substring_number_from_name()\fP function returns
+the error PCRE2_ERROR_NOUNIQUESUBSTRING.
 .P
 If you want to get full details of all captured substrings for a given name,
 you must use the \fBpcre2_substring_nametable_scan()\fP function. The first
 argument is the compiled pattern, and the second is the name. If the third and
-fourth arguments are NULL, the function returns a group number (it is not
-defined which). Otherwise, the third and fourth arguments must be pointers to
+fourth arguments are NULL, the function returns a group number for a unique
+name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise.
+.P
+When the third and fourth arguments are not NULL, they must be pointers to
 variables that are updated by the function. After it has run, they point to the
 first and last entries in the name-to-number table for the given name, and the
-function returns the length of each entry. In both cases,
+function returns the length of each entry in code units. In both cases,
 PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name.
 .P
 The format of the name table is described above in the section entitled
@@ -2476,15 +2483,15 @@ Given all the relevant entries for the name, you can extract each of their
 numbers, and hence the captured data.
 .
 .
-.SH "FINDING ALL POSSIBLE MATCHES"
+.SH "FINDING ALL POSSIBLE MATCHES AT ONE POSITION"
 .rs
 .sp
 The traditional matching function uses a similar algorithm to Perl, which stops
-when it finds the first match, starting at a given point in the subject. If you
-want to find all possible matches, or the longest possible match at a given
-position, consider using the alternative matching function (see below) instead.
-If you cannot use the alternative function, you can kludge it up by making use
-of the callout facility, which is described in the
+when it finds the first match at a given point in the subject. If you want to
+find all possible matches, or the longest possible match at a given position,
+consider using the alternative matching function (see below) instead. If you
+cannot use the alternative function, you can kludge it up by making use of the
+callout facility, which is described in the
 .\" HREF
 \fBpcre2callout\fP
 .\"
@@ -2628,11 +2635,10 @@ the longest matches.
 .P
 NOTE: PCRE2's "auto-possessification" optimization usually applies to character
 repeats at the end of a pattern (as well as internally). For example, the
-pattern "a\ed+" is compiled as if it were "a\ed++" because there is no point in
-backtracking into the repeated digits. For DFA matching, this means that only
-one possible match is found. If you really do want multiple matches in such
-cases, either use an ungreedy repeat ("a\ed+?") or set the
-PCRE2_NO_AUTO_POSSESS option when compiling.
+pattern "a\ed+" is compiled as if it were "a\ed++". For DFA matching, this
+means that only one possible match is found. If you really do want multiple
+matches in such cases, either use an ungreedy repeat auch as "a\ed+?" or set
+the PCRE2_NO_AUTO_POSSESS option when compiling.
 .
 .
 .SS "Error returns from \fBpcre2_dfa_match()\fP"
@@ -2673,7 +2679,7 @@ extremely rare, as a vector of size 1000 is used.
 .sp
   PCRE2_ERROR_DFA_BADRESTART
 .sp
-When \fBpcre2_dfa_match()\fP is called with the \fBpcre2_dfa_RESTART\fP option,
+When \fBpcre2_dfa_match()\fP is called with the \fBPCRE2_DFA_RESTART\fP option,
 some plausibility checks are made on the contents of the workspace, which
 should contain data about the previous partial match. If any of these checks
 fail, this error is given.
@@ -2682,9 +2688,9 @@ fail, this error is given.
 .SH "SEE ALSO"
 .rs
 .sp
-\fBpcre2build\fP(3), \fBpcre2libs\fP(3), \fBpcre2callout\fP(3),
+\fBpcre2build\fP(3), \fBpcre2callout\fP(3), \fBpcre2demo(3)\fP,
 \fBpcre2matching\fP(3), \fBpcre2partial\fP(3), \fBpcre2posix\fP(3),
-\fBpcre2demo(3)\fP, \fBpcre2sample\fP(3), \fBpcre2stack\fP(3).
+\fBpcre2sample\fP(3), \fBpcre2stack\fP(3), \fBpcre2unicode\fP(3).
 .
 .
 .SH AUTHOR
@@ -2701,6 +2707,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 18 November 2014
+Last updated: 21 November 2014
 Copyright (c) 1997-2014 University of Cambridge.
 .fi
diff --git a/src/pcre2_jit_compile.c b/src/pcre2_jit_compile.c
index 9788b9d..5b431bc 100644
--- a/src/pcre2_jit_compile.c
+++ b/src/pcre2_jit_compile.c
@@ -3438,10 +3438,10 @@ while (TRUE)
       }
     }
   else
-    { 
+    {
     caseless = FALSE;
-    othercase[0] = 0; /* Stops compiler warning - PH */ 
-    } 
+    othercase[0] = 0; /* Stops compiler warning - PH */
+    }
 
   len_save = len;
   cc_save = cc;
diff --git a/src/pcre2_match.c b/src/pcre2_match.c
index f03f3ed..b3dc0c3 100644
--- a/src/pcre2_match.c
+++ b/src/pcre2_match.c
@@ -1401,11 +1401,11 @@ for (;;)
         condition = TRUE;
 
         /* Advance ecode past the assertion to the start of the first branch,
-        but adjust it so that the general choosing code below works. If the 
-        assertion has a quantifier that allows zero repeats we must skip over 
+        but adjust it so that the general choosing code below works. If the
+        assertion has a quantifier that allows zero repeats we must skip over
         the BRAZERO. This is a lunatic thing to do, but somebody did! */
-        
-        if (*ecode == OP_BRAZERO) ecode++; 
+
+        if (*ecode == OP_BRAZERO) ecode++;
         ecode += GET(ecode, 1);
         while (*ecode == OP_ALT) ecode += GET(ecode, 1);
         ecode += 1 + LINK_SIZE - PRIV(OP_lengths)[condcode];