pcre2/doc/pcre2api.3

.TH PCRE2API 3 "05 October 2014" "PCRE2 10.00"
.SH NAME
PCRE2 - Perl-compatible regular expressions (revised API)
.sp
.B #include <pcre2.h>
.sp
PCRE2 is a new API for PCRE. This document contains a description of all its
functions. See the
.\" HREF
\fBpcre2\fP
.\"
document for an overview of all the PCRE2 documentation.
.
.
.SH "PCRE2 NATIVE API BASIC FUNCTIONS"
.rs
.sp
.nf
.B pcre2_code *pcre2_compile(PCRE2_SPTR \fIpattern\fP, PCRE2_SIZE \fIlength\fP,
.B "  uint32_t \fIoptions\fP, int *\fIerrorcode\fP, PCRE2_SIZE *\fIerroroffset,\fP"
.B "  pcre2_compile_context *\fIccontext\fP);"
.sp
.B pcre2_code_free(pcre2_code *\fIcode\fP);
.sp
.B pcre2_match_data_create(uint32_t \fIovecsize\fP,
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B pcre2_match_data_create_from_pattern(pcre2_code *\fIcode\fP,
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B int pcre2_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
.B "  pcre2_match_context *\fImcontext\fP);"
.sp
.B int pcre2_dfa_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
.B "  pcre2_match_context *\fImcontext\fP,"
.B "  int *\fIworkspace\fP, PCRE2_SIZE \fIwscount\fP);"
.sp
.B void pcre2_match_data_free(pcre2_match_data *\fImatch_data\fP);
.fi
.
.
.SH "PCRE2 NATIVE API AUXILIARY MATCH FUNCTIONS"
.rs
.sp
.nf
.B PCRE2_SIZE pcre2_get_leftchar(pcre2_match_data *\fImatch_data\fP);
.sp
.B PCRE2_SPTR pcre2_get_mark(pcre2_match_data *\fImatch_data\fP);
.sp
.B uint32_t pcre2_get_ovector_count(pcre2_match_data *\fImatch_data\fP);
.sp
.B PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *\fImatch_data\fP);
.sp
.B PCRE2_SIZE pcre2_get_rightchar(pcre2_match_data *\fImatch_data\fP);
.sp
.B PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *\fImatch_data\fP);
.fi
.
.
.SH "PCRE2 NATIVE API GENERAL CONTEXT FUNCTIONS"
.rs
.sp
.nf
.B pcre2_general_context *pcre2_general_context_create(
.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
.sp
.B pcre2_general_context *pcre2_general_context_copy(
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B void pcre2_general_context_free(pcre2_general_context *\fIgcontext\fP);
.fi
.
.
.SH "PCRE2 NATIVE API COMPILE CONTEXT FUNCTIONS"
.rs
.sp
.nf
.B pcre2_compile_context *pcre2_compile_context_create(
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B pcre2_compile_context *pcre2_compile_context_copy(
.B "  pcre2_compile_context *\fIccontext\fP);"
.sp
.B void pcre2_compile_context_free(pcre2_compile_context *\fIccontext\fP);
.sp
.B int pcre2_set_bsr(pcre2_compile_context *\fIccontext\fP,
.B "  uint32_t \fIvalue\fP);"
.sp
.B int pcre2_set_character_tables(pcre2_compile_context *\fIccontext\fP,
.B "  const unsigned char *\fItables\fP);"
.sp
.B int pcre2_set_newline(pcre2_compile_context *\fIccontext\fP,
.B "  uint32_t \fIvalue\fP);"
.sp
.B int pcre2_set_parens_nest_limit(pcre2_compile_context *\fIccontext\fP,
.B "  uint32_t \fIvalue\fP);"
.sp
.B int pcre2_set_compile_recursion_guard(pcre2_compile_context *\fIccontext\fP,
.B "  int (*\fIguard_function\fP)(uint32_t));"
.fi
.
.
.SH "PCRE2 NATIVE API MATCH CONTEXT FUNCTIONS"
.rs
.sp
.nf
.B pcre2_match_context *pcre2_match_context_create(
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B pcre2_match_context *pcre2_match_context_copy(
.B "  pcre2_match_context *\fImcontext\fP);"
.sp
.B void pcre2_match_context_free(pcre2_match_context *\fImcontext\fP);
.sp
.B int pcre2_set_callout(pcre2_match_context *\fImcontext\fP,
.B "  int (*\fIcallout_function\fP)(pcre2_callout_block *),"
.B "  void *\fIcallout_data\fP);"
.sp
.B int pcre2_set_match_limit(pcre2_match_context *\fImcontext\fP,
.B "  uint32_t \fIvalue\fP);"
.sp
.B int pcre2_set_recursion_limit(pcre2_match_context *\fImcontext\fP,
.B "  uint32_t \fIvalue\fP);"
.sp
.B int pcre2_set_recursion_memory_management(
.B "  pcre2_match_context *\fImcontext\fP,"
.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
.fi
.
.
.SH "PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS"
.rs
.sp
.nf
.B int pcre2_substring_copy_byname(pcre2_match_data *\fImatch_data\fP,
.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR *\fIbuffer\fP, PCRE2_SIZE *\fIbufflen\fP);"
.sp
.B int pcre2_substring_copy_bynumber(pcre2_match_data *\fImatch_data\fP,
.B "  unsigned int \fInumber\fP, PCRE2_UCHAR *\fIbuffer\fP,"
.B "  PCRE2_SIZE *\fIbufflen\fP);"
.sp
.B void pcre2_substring_free(PCRE2_UCHAR *\fIbuffer\fP);
.sp
.B int pcre2_substring_get_byname(pcre2_match_data *\fImatch_data\fP,
.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR **\fIbufferptr\fP, PCRE2_SIZE *\fIbufflen\fP);"
.sp
.B int pcre2_substring_get_bynumber(pcre2_match_data *\fImatch_data\fP,
.B "  unsigned int \fInumber\fP, PCRE2_UCHAR **\fIbufferptr\fP,"
.B "  PCRE2_SIZE *\fIbufflen\fP);"
.sp
.B int pcre2_substring_length_byname(pcre2_match_data *\fImatch_data\fP,
.B "  PCRE2_SPTR \fIname\fP, PCRE2_SIZE *\fIlength\fP);"
.sp
.B int pcre2_substring_length_bynumber(pcre2_match_data *\fImatch_data\fP,
.B "  unsigned int \fInumber\fP, PCRE2_SIZE *\fIlength\fP);"
.sp
.B int pcre2_substring_nametable_scan(const pcre2_code *\fIcode\fP,
.B "  PCRE2_SPTR \fIname\fP, PCRE2_SPTR *\fIfirst\fP, PCRE2_SPTR *\fIlast\fP);"
.sp
.B int pcre2_substring_number_from_name(const pcre2_code *\fIcode\fP,
.B "  PCRE2_SPTR \fIname\fP);"
.sp
.B void pcre2_substring_list_free(PCRE2_SPTR *\fIlist\fP);
.sp
.B int pcre2_substring_list_get(pcre2_match_data *\fImatch_data\fP,
.B "  PCRE2_UCHAR ***\fIlistptr\fP, PCRE2_SIZE **\fIlengthsptr\fP);
.fi
.
.
.SH "PCRE2 NATIVE API JIT FUNCTIONS"
.rs
.sp
.nf
.B int pcre2_jit_compile(pcre2_code *\fIcode\fP, uint32_t \fIoptions\fP);
.sp
.B int pcre2_jit_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
.B "  pcre2_match_context *\fImcontext\fP, pcre2_jit_stack *\fIjit_stack\fP);"
.sp
.B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP);
.sp
.B pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *\fIgcontext\fP,
.B "  PCRE2_SIZE \fIstartsize\fP, PCRE2_SIZE \fImaxsize\fP);"
.sp
.B void pcre2_jit_stack_assign(const pcre2_code *\fIcode\fP,
.B "  pcre2_jit_callback \fIcallback_function\fP, void *\fIcallback_data\fP);"
.sp
.B void pcre2_jit_stack_free(pcre2_jit_stack *\fIjit_stack\fP);
.fi
.
.
.SH "PCRE2 NATIVE API AUXILIARY FUNCTIONS"
.rs
.sp
.nf
.B int pcre2_get_error_message(int \fIerrorcode\fP, PCRE2_UCHAR *\fIbuffer\fP,
.B "  PCRE2_SIZE \fIbufflen\fP);"
.sp
.B const unsigned char *pcre2_maketables(pcre2_general_context *\fIgcontext\fP);
.sp
.B int pcre2_pattern_info(const pcre2 *\fIcode\fP, uint32_t \fIwhat\fP, void *\fIwhere\fP);
.sp
.B int pcre2_config(uint32_t \fIwhat\fP, void *\fIwhere\fP, PCRE2_SIZE \fIlength\fP);
.fi
.
.
.SH "PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES"
.rs
.sp
There are three PCRE2 libraries, supporting 8-bit, 16-bit, and 32-bit code
units, respectively. However, there is just one header file, \fBpcre2.h\fP.
This contains the function prototypes and other definitions for all three
libraries. One, two, or all three can be installed simultaneously. On Unix-like
systems the libraries are called \fBlibpcre2-8\fP, \fBlibpcre2-16\fP, and
\fBlibpcre2-32\fP, and they can also co-exist with the original PCRE libraries.
.P
Character strings are passed to and from a PCRE2 library as a sequence of
unsigned integers in code units of the appropriate width. Every PCRE2 function
comes in three different forms, one for each library, for example:
.sp
  \fBpcre2_compile_8()\fP
  \fBpcre2_compile_16()\fP
  \fBpcre2_compile_32()\fP
.sp
There are also three different sets of data types:
.sp
  \fBPCRE2_UCHAR8, PCRE2_UCHAR16, PCRE2_UCHAR32\fP
  \fBPCRE2_SPTR8,  PCRE2_SPTR16,  PCRE2_SPTR32\fP
.sp
The UCHAR types define unsigned code units of the appropriate widths. For
example, PCRE2_UCHAR16 is usually defined as `uint16_t'. The SPTR types are
constant pointers to the equivalent UCHAR types, that is, they are pointers to
vectors of unsigned code units.
.P
Many applications use only one code unit width. For their convenience, macros
are defined whose names are the generic forms such as \fBpcre2_compile()\fP and
PCRE2_SPTR. These macros use the value of the macro PCRE2_CODE_UNIT_WIDTH to
generate the appropriate width-specific function and macro names.
PCRE2_CODE_UNIT_WIDTH is not defined by default. An application must define it
to be 8, 16, or 32 before including \fBpcre2.h\fP in order to make use of the
generic names.
.P
Applications that use more than one code unit width can be linked with more
than one PCRE2 library, but must define PCRE2_CODE_UNIT_WIDTH to be 0 before
including \fBpcre2.h\fP, and then use the real function names. Any code that is
to be included in an environment where the value of PCRE2_CODE_UNIT_WIDTH is
unknown should also use the real function names. (Unfortunately, it is not
possible in C code to save and restore the value of a macro.)
.P
If PCRE2_CODE_UNIT_WIDTH is not defined before including \fBpcre2.h\fP, a 
compiler error occurs.
.P
When using multiple libraries in an application, you must take care when
processing any particular pattern to use only functions from a single library.
For example, if you want to run a match using a pattern that was compiled with
\fBpcre2_compile_16()\fP, you must do so with \fBpcre2_match_16()\fP, not
\fBpcre2_match_8()\fP.
.P
In the function summaries above, and in the rest of this document and other
PCRE2 documents, functions and data types are described using their generic
names, without the 8, 16, or 32 suffix.
.
.
.SH "PCRE2 API OVERVIEW"
.rs
.sp
PCRE2 has its own native API, which is described in this document. There are
also some wrapper functions for the 8-bit library that correspond to the
POSIX regular expression API, but they do not give access to all the
functionality. They are described in the
.\" HREF
\fBpcre2posix\fP
.\"
documentation. Both these APIs define a set of C function calls.
.P
The native API C data types, function prototypes, option values, and error
codes are defined in the header file \fBpcre2.h\fP, which contains definitions
of PCRE2_MAJOR and PCRE2_MINOR, the major and minor release numbers for the
library. Applications can use these to include support for different releases
of PCRE2.
.P
In a Windows environment, if you want to statically link an application program
against a non-dll PCRE2 library, you must define PCRE2_STATIC before including
\fBpcre2.h\fP.
.P
The functions \fBpcre2_compile()\fP, and \fBpcre2_match()\fP are used for
compiling and matching regular expressions in a Perl-compatible manner. A
sample program that demonstrates the simplest way of using them is provided in
the file called \fIpcre2demo.c\fP in the PCRE2 source distribution. A listing
of this program is given in the
.\" HREF
\fBpcre2demo\fP
.\"
documentation, and the
.\" HREF
\fBpcre2sample\fP
.\"
documentation describes how to compile and run it.
.P
Just-in-time compiler support is an optional feature of PCRE2 that can be built
in appropriate hardware environments. It greatly speeds up the matching
performance of many patterns. Programs can request that it be used if
available, by calling \fBpcre2_jit_compile()\fP after a pattern has been
successfully compiled by \fBpcre2_compile()\fP. This does nothing if JIT
support is not available.
.P
More complicated programs might need to make use of the specialist functions
\fBpcre2_jit_stack_alloc()\fP, \fBpcre2_jit_stack_free()\fP, and
\fBpcre2_jit_stack_assign()\fP in order to control the JIT code's memory usage.
.P
JIT matching is automatically used by \fBpcre2_match()\fP if it is available.
There is also a direct interface for JIT matching, which gives improved
performance. The JIT-specific functions are discussed in the
.\" HREF
\fBpcre2jit\fP
.\"
documentation.
.P
A second matching function, \fBpcre2_dfa_exec()\fP, which is not
Perl-compatible, is also provided. This uses a different algorithm for the
matching. The alternative algorithm finds all possible matches (at a given
point in the subject), and scans the subject just once (unless there are
lookbehind assertions). However, this algorithm does not return captured
substrings. A description of the two matching algorithms and their advantages
and disadvantages is given in the
.\" HREF
\fBpcre2matching\fP
.\"
documentation. There is no JIT support for \fBpcre2_dfa_match()\fP.
.P
In addition to the main compiling and matching functions, there are convenience
functions for extracting captured substrings from a subject string that is
matched by \fBpcre2_match()\fP. They are:
.sp
  \fBpcre2_substring_copy_byname()\fP
  \fBpcre2_substring_copy_bynumber()\fP
  \fBpcre2_substring_get_byname()\fP
  \fBpcre2_substring_get_bynumber()\fP
  \fBpcre2_substring_list_get()\fP
  \fBpcre2_substring_length_byname()\fP
  \fBpcre2_substring_length_bynumber()\fP
  \fBpcre2_substring_nametable_scan()\fP
  \fBpcre2_substring_number_from_name()\fP
.sp
\fBpcre2_substring_free()\fP and \fBpcre2_substring_list_free()\fP are also
provided, to free the memory used for extracted strings.
.P
There are functions for finding out information about a compiled pattern
(\fBpcre2_pattern_info()\fP) and about the configuration with which PCRE2 was
built (\fBpcre2_config()\fP).
.
.
.\" HTML <a name="newlines"></a>
.SH NEWLINES
.rs
.sp
PCRE2 supports five different conventions for indicating line breaks in
strings: a single CR (carriage return) character, a single LF (linefeed)
character, the two-character sequence CRLF, any of the three preceding, or any
Unicode newline sequence. The Unicode newline sequences are the three just
mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
(paragraph separator, U+2029).
.P
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.
.P
The newline convention can be changed when calling \fBpcre2_compile()\fP, or it
can be specified by special text at the start of the pattern itself; this
overrides any other settings. See the
.\" HREF
\fBpcre2pattern\fP
.\"
page for details of the special character sequences.
.P
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 dollar
metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
recognized line ending sequence, the match position advancement for a
non-anchored pattern. There is more detail about this in the
.\" HTML <a href="#matchoptions">
.\" </a>
section on \fBpcre2_match()\fP options
.\"
below.
.P
The choice of newline convention does not affect the interpretation of
the \en or \er escape sequences, nor does it affect what \eR matches, which has 
its own separate control.
.
.
.SH MULTITHREADING
.rs
.sp
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 applications can use it.
.P
There are several different blocks of data that are used to pass information
between the application and the PCRE libraries.
.P
(1) A pointer to the compiled form of a pattern is returned to the user when
\fBpcre2_compile()\fP 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 than one thread
simultaneously. An application can compile all its patterns 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
.\" HREF
\fBpcre2jit\fP
.\"
documentation for more details.
.P
(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 API. Many straightforward applications will
not need to use contexts.
.P
In a multithreaded application, if the parameters in a context are values 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.
.P
(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 memory.
.
.
.SH "PCRE2 CONTEXTS"
.rs
.sp
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 \fBcontext\fP 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.
.P
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.
.
.
.SS "The general context"
.rs
.sp
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 created by:
.sp
.nf
.B pcre2_general_context *pcre2_general_context_create(
.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
.fi
.sp
The two function pointers specify custom memory management functions, whose
prototypes are:
.sp
  \fBvoid *private_malloc(PCRE2_SIZE, void *);\fP
  \fBvoid  private_free(void *, void *);\fP
.sp
Whenever code in PCRE2 calls these functions, the final argument is the value
of \fImemory_data\fP. Either of the first two arguments of the creation
function may be NULL, in which case the system memory management functions
\fImalloc()\fP and \fIfree()\fP are used. (This is not currently useful, as
there are no other fields in a general context, but in future there might be.)
The \fIprivate_malloc()\fP function is used (if supplied) to obtain memory for
storing the context, and all three values are saved as part of the context.
.P
Whenever PCRE2 creates a data block of any kind, the block contains a pointer
to the \fIfree()\fP function that matches the \fImalloc()\fP function that was
used. When the time comes to free the block, this function is called.
.P
A general context can be copied by calling:
.sp
.nf
.B pcre2_general_context *pcre2_general_context_copy(
.B "  pcre2_general_context *\fIgcontext\fP);"
.fi
.sp
The memory used for a general context should be freed by calling:
.sp
.nf
.B void pcre2_general_context_free(pcre2_general_context *\fIgcontext\fP);
.fi
.sp
.
.
.\" HTML <a name="compilecontext"></a>
.SS "The compile context"
.rs
.sp
A compile context is required if you want to change the default values of any 
of the following compile-time parameters:
.sp
  What \eR 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.
.sp
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
\fIpcre2_compile()\fP.
.P
A compile context is created, copied, and freed by the following functions:
.sp
.nf
.B pcre2_compile_context *pcre2_compile_context_create(
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B pcre2_compile_context *pcre2_compile_context_copy(
.B "  pcre2_compile_context *\fIccontext\fP);"
.sp
.B void pcre2_compile_context_free(pcre2_compile_context *\fIccontext\fP);
.fi
.sp
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.
.sp
.nf
.B int pcre2_set_bsr(pcre2_compile_context *\fIccontext\fP,
.B "  uint32_t \fIvalue\fP);"
.fi
.sp
The value must be PCRE2_BSR_ANYCRLF, to specify that \eR matches only CR, LF, 
or CRLF, or PCRE2_BSR_UNICODE, to specify that \eR 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, \fIpcre2_match()\fP and 
\fIpcre2_dfa_match()\fP.
.sp
.nf
.B int pcre2_set_character_tables(pcre2_compile_context *\fIccontext\fP,
.B "  const unsigned char *\fItables\fP);"
.fi
.sp
The value must be the result of a call to \fIpcre2_maketables()\fP, whose only 
argument is a general context. This function builds a set of character tables
in the current locale.
.sp
.nf
.B int pcre2_set_newline(pcre2_compile_context *\fIccontext\fP,
.B "  uint32_t \fIvalue\fP);"
.fi
.sp
This specifies which characters or character sequences are to be recognized as 
newlines. The value must be one of PCRE2_NEWLINE_CR (carriage return only),
PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the two-character 
sequence CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any of the above), or
PCRE2_NEWLINE_ANY (any Unicode newline sequence).
.P
When a pattern is compiled with the PCRE2_EXTENDED option, the value of this
parameter affects the recognition of white space and the end of internal
comments starting with #. The value is saved with the compiled pattern for
subsequent use by the JIT compiler and by the two interpreted matching
functions, \fIpcre2_match()\fP and \fIpcre2_dfa_match()\fP.
.sp
.nf
.B int pcre2_set_parens_nest_limit(pcre2_compile_context *\fIccontext\fP,
.B "  uint32_t \fIvalue\fP);"
.fi
.sp
This parameter ajusts the limit, set when PCRE2 is built (default 250), on the
depth of parenthesis nesting in a pattern. This limit stops rogue patterns
using up too much system stack when being compiled.
.sp
.nf
.B int pcre2_set_compile_recursion_guard(pcre2_compile_context *\fIccontext\fP,
.B "  int (*\fIguard_function\fP)(uint32_t));"
.fi
.sp
There is at least one application that runs PCRE2 in threads with very limited
system stack, where running out of stack is to be avoided at all costs. The 
parenthesis limit above cannot take account of how much stack is actually
available. For a finer control, you can supply a function that is called
whenever \fBpcre2_compile()\fP starts to compile a parenthesized part of a
pattern. The argument to the function gives the current depth of nesting. The
function should return zero if all is well, or non-zero to force an error.
.
.
.\" HTML <a name="matchcontext"></a>
.SS "The match context"
.rs
.sp
A match context is required if you want to change the default values of any 
of the following match-time parameters:
.sp
  What \eR matches (Unicode newlines or CR, LF, CRLF only);
  A callout function;
  The limit for calling \fImatch()\fP;  
  The limit for calling \fImatch()\fP recursively;
  The newline character sequence;
.sp
A match context is also required if you are using custom memory management. 
If none of these apply, just pass NULL as the context argument of 
\fBpcre2_match()\fP, \fBpcre2_dfa_match()\fP, or \fBpcre2_jit_match()\fP.
Changing the newline value or what \eR matches at match time disables the use 
of JIT via \fBpcre2_match()\fP.  
.P
A match context is created, copied, and freed by the following functions:
.sp
.nf
.B pcre2_match_context *pcre2_match_context_create(
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B pcre2_match_context *pcre2_match_context_copy(
.B "  pcre2_match_context *\fImcontext\fP);"
.sp
.B void pcre2_match_context_free(pcre2_match_context *\fImcontext\fP);
.fi
.sp
A match 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.
.sp
.nf
.B int pcre2_set_callout(pcre2_match_context *\fImcontext\fP,
.B "  int (*\fIcallout_function\fP)(pcre2_callout_block *),"
.B "  void *\fIcallout_data\fP);"
.fi
.sp
This sets up a "callout" function, which PCRE2 will call at specified points
during a matching operation. Details are given in the
.\" HREF
\fBpcre2callout\fP
.\"
documentation.
.sp
.nf
.B int pcre2_set_match_limit(pcre2_match_context *\fImcontext\fP,
.B "  uint32_t \fIvalue\fP);"
.fi
.sp
The \fImatch_limit\fP parameter provides a means of preventing PCRE2 from using
up too many resources when processing patterns that are not going to match, but
which have a very large number of possibilities in their search trees. The
classic example is a pattern that uses nested unlimited repeats.
.P
Internally, \fBpcre2_match()\fP uses a function called \fBmatch()\fP, which it
calls repeatedly (sometimes recursively). The limit set by \fImatch_limit\fP is
imposed on the number of times this function is called during a match, which
has the effect of limiting the amount of backtracking that can take place. For
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 studied
with \fBpcre2_jit_compile()\fP, 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 \fImatch_limit\fP value is also
used in this case (but in a different way) to limit how long the matching can
continue.
.P
The default value for the limit can be set when PCRE2 is built; the default
default is 10 million, which handles all but the most extreme cases. If the
limit is exceeded, \fBpcre2_match()\fP returns PCRE2_ERROR_MATCHLIMIT. A value
for the match limit may also be supplied by an item at the start of a pattern
of the form
.sp
  (*LIMIT_MATCH=ddd)
.sp
where ddd is a decimal number. However, such a setting is ignored unless ddd is
less than the limit set by the caller of \fBpcre2_match()\fP or, if no such
limit is set, less than the default.
.sp
.nf
.B int pcre2_set_recursion_limit(pcre2_match_context *\fImcontext\fP,
.B "  uint32_t \fIvalue\fP);"
.fi
.sp
The \fIrecursion_limit\fP parameter is similar to \fImatch_limit\fP, but
instead of limiting the total number of times that \fBmatch()\fP is called, it
limits the depth of recursion. The recursion depth is a smaller number than the
total number of calls, because not all calls to \fBmatch()\fP are recursive.
This limit is of use only if it is set smaller than \fImatch_limit\fP.
.P
Limiting the recursion depth limits the amount of system stack that can be
used, or, when PCRE2 has been compiled to use memory on the heap instead of the
stack, the amount of heap memory that can be used. This limit is not relevant,
and is ignored, when matching is done using JIT compiled code or by the 
\fBpcre2_dfa_match()\fP function.
.P
The default value for \fIrecursion_limit\fP can be set when PCRE2 is built; the
default default is the same value as the default for \fImatch_limit\fP. If the
limit is exceeded, \fBpcre2_match()\fP returns PCRE2_ERROR_RECURSIONLIMIT. A
value for the recursion limit may also be supplied by an item at the start of a
pattern of the form
.sp
  (*LIMIT_RECURSION=ddd)
.sp
where ddd is a decimal number. However, such a setting is ignored unless ddd is
less than the limit set by the caller of \fBpcre2_match()\fP or, if no such
limit is set, less than the default.
.sp
.nf
.B int pcre2_set_recursion_memory_management(
.B "  pcre2_match_context *\fImcontext\fP,"
.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
.B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
.fi
.sp
This function sets up two additional custom memory management functions for use 
by \fBpcre2_match()\fP when PCRE2 is compiled to use the heap for remembering
backtracking data, instead of recursive function calls that use the system 
stack. There is a discussion about PCRE2's stack usage in the
.\" HREF
\fBpcre2stack\fP
.\"
documentation. See the
.\" HREF
\fBpcre2build\fP
.\"
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,
\fBpcre2_match()\fP 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 \fBpcre2_match()\fP 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.
.
.
.SH "CHECKING BUILD-TIME OPTIONS"
.rs
.sp
.B int pcre2_config(uint32_t \fIwhat\fP, void *\fIwhere\fP, PCRE2_SIZE \fIlength\fP);
.P
The function \fBpcre2_config()\fP makes it possible for a PCRE2 client to
discover which optional features have been compiled into the PCRE2 library. The
.\" HREF
\fBpcre2build\fP
.\"
documentation has more details about these optional features.
.P
The first argument for \fBpcre2_config()\fP specifies which information is
required. The second argument is a pointer to memory into which the information
is placed, with the final argument giving the length of this memory in bytes.
For calls that return numerical values, \fIwhere\fP should point to
appropriately aligned memory, with \fIlength\fP set to at least the "sizeof"
the data type.
.P
The returned value from \fBpcre2_config()\fP is zero on success, or the
negative error code PCRE2_ERROR_BADOPTION if the value in the first argument is
not recognized. The following information is available:
.sp
  PCRE2_CONFIG_BSR
.sp
The output is an integer whose value indicates what character sequences the \eR
escape sequence matches by default. A value of 0 means that \eR matches any
Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
or CRLF. The default can be overridden when a pattern is compiled or matched.
.sp
  PCRE2_CONFIG_JIT
.sp
The output is an integer that is set to one if support for just-in-time
compiling is available; otherwise it is set to zero.
.sp
  PCRE2_CONFIG_JITTARGET
.sp
FIXME: this needs sorting out once JIT is implemented.
If JIT support is available, the string 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, FIXME.
.sp
  PCRE2_CONFIG_LINKSIZE
.sp
The output is an integer that contains the number of bytes used for internal
linkage in compiled regular expressions. When PCRE2 is configured, the value
can be set to 2, 3, or 4, with the default being 2. This is the value that is 
returned by \fBpcre2_config()\fP. 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, so the configured value is not relevant.
.P
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 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 expense of slower matching.
.sp
  PCRE2_CONFIG_MATCHLIMIT
.sp
The output is an unsigned long integer that gives the default limit for the
number of internal matching function calls in a \fBpcre2_match()\fP execution.
Further details are given with \fBpcre2_match()\fP below.
.sp
  PCRE2_CONFIG_NEWLINE
.sp
The output is an integer whose value specifies the default character sequence
that is recognized as meaning "newline". The values are:
.sp
  1  Carriage return (CR)
  2  Linefeed (LF)
  3  Carriage return, linefeed (CRLF)
  4  Any Unicode line ending
  5  Any of CR, LF, or CRLF
.sp       
The default should normally correspond to the standard sequence for your
operating system.
.sp
  PCRE2_CONFIG_PARENSLIMIT
.sp
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 compiled. 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 \fBpcre2_set_compile_recursion_guard()\fP.
.sp
  PCRE2_CONFIG_RECURSIONLIMIT
.sp
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
\fBpcre2_match()\fP execution. Further details are given with
\fBpcre2_match()\fP below.
.sp
  PCRE2_CONFIG_STACKRECURSE
.sp
The output is an integer that is set to one if internal recursion when running
\fBpcre2_match()\fP 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.
.sp
  PCRE2_CONFIG_UNICODE_VERSION
.sp   
The \fIwhere\fP argument should point to a buffer that is at least 24 code
units long. If PCRE2 has been compiled without Unicode support, this is filled
with the text "Unicode not supported". Otherwise, the Unicode version string
(for example, "7.0.0") is returnd. The string is zero-terminated.
.sp
  PCRE2_CONFIG_UNICODE
.sp
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.
.sp
  PCRE2_CONFIG_VERSION
.sp
The \fIwhere\fP argument should point to a buffer that is at least 12 code 
units long. It is filled with the PCRE2 version string, zero-terminated.   
.
.
.SH "COMPILING A PATTERN"
.rs
.sp
.nf
.B pcre2_code *pcre2_compile(PCRE2_SPTR \fIpattern\fP, PCRE2_SIZE \fIlength\fP,
.B "  uint32_t \fIoptions\fP, int *\fIerrorcode\fP, PCRE2_SIZE *\fIerroroffset,\fP"
.B "  pcre2_compile_context *\fIccontext\fP);"
.sp
.B pcre2_code_free(pcre2_code *\fIcode\fP);
.fi
.P
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 \fBpcre2_code_free()\fP when 
it is no longer needed.
.P
If the compile context argument \fIccontext\fP is NULL, the memory is obtained 
by calling \fBmalloc()\fP. Otherwise, it is obtained from the same memory 
function that was used for the compile context.
.P
The \fIoptions\fP argument contains various bit settings that affect the
compilation. 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
.\" HREF
\fBpcre2pattern\fP
.\"
documentation). 
.P
For those options that can be different in different parts of the pattern, the
contents of the \fIoptions\fP 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.
.P
Other, less frequently required compile-time parameters (for example, the 
newline setting) can be provided in a compile context (as described
.\" HTML <a href="#compilecontext">
.\" </a>
above).
.\"
.P
If \fIerrorcode\fP or \fIerroroffset\fP is NULL, \fBpcre2_compile()\fP returns
NULL immediately. Otherwise, if compilation of a pattern fails,
\fBpcre2_compile()\fP returns NULL, having set these variables to an error code
and an offset (number of code units) within the pattern, respectively. The
\fBpcre2_get_error_message()\fP 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.
.P
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 character.
.P
This code fragment shows a typical straightforward call to
\fBpcre2_compile()\fP:
.sp
  pcre2_code *re;
  PCRE2_SIZE erroffset;
  int errorcode; 
  re = pcre2_compile(
    "^A.*Z",                /* the pattern */
    PCRE2_ZERO_TERMINATED,  /* the pattern is zero-terminated */ 
    0,                      /* default options */
    &errorcode,             /* for error code */
    &erroffset,             /* for error offset */
    NULL);                  /* no compile context */
.sp
The following names for option bits are defined in the \fBpcre2.h\fP header
file:
.sp
  PCRE2_ANCHORED
.sp
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 only way to do it in
Perl.
.sp
  PCRE2_ALLOW_EMPTY_CLASS
.sp
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. 
.sp
  PCRE2_ALT_BSUX
.sp
This option request alternative handling of three escape sequences, which 
makes PCRE2's behaviour more like ECMAscript (aka JavaScript). When it is set:
.P
(1) \eU matches an upper case "U" character; by default \eU causes a compile
time error (Perl uses \eU to upper case subsequent characters).
.P
(2) \eu 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, \eu causes a compile time error (Perl uses it to upper
case the following character).
.P
(3) \ex 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
\ex, but it may have zero, one, or two digits (so, for example, \exz matches a
binary zero character followed by z).
.sp
  PCRE2_AUTO_CALLOUT
.sp
If this bit is set, \fBpcre2_compile()\fP automatically inserts callout items,
all with number 255, before each pattern item. For discussion of the callout
facility, see the
.\" HREF
\fBpcre2callout\fP
.\"
documentation.
.sp
  PCRE2_CASELESS
.sp
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. 
.sp
  PCRE2_DOLLAR_ENDONLY
.sp
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.
.sp
  PCRE2_DOTALL
.sp
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 subject 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 negative class such as [^a] always matches newline
characters, independent of the setting of this option.
.sp
  PCRE2_DUPNAMES
.sp
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 the
.\" HREF
\fBpcre2pattern\fP
.\"
documentation.
.sp
  PCRE2_EXTENDED
.sp
If this bit is set, most white space characters in the pattern are totally
ignored except when escaped or inside a character class. However, white space
is not allowed within sequences such as (?> that introduce various
parenthesized subpatterns, nor within numerical quantifiers such as {1,3}.
Ignorable white space is permitted between an item and a following quantifier
and between a quantifier and a following + that indicates possessiveness.
.P
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 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 changed within a pattern by a
(?x) option setting.
.P
Which characters are interpreted as newlines can be specified by a setting in
the compile context that is passed to \fBpcre2_compile()\fP or by a special
sequence at the start of the pattern, as described in the section entitled
.\" HTML <a href="pcrepattern.html#newlines">
.\" </a>
"Newline conventions"
.\"
in the \fBpcre2pattern\fP documentation. A default is defined when PCRE2 is 
built.
.sp
  PCRE2_FIRSTLINE
.sp
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.
.sp
  PCRE2_MATCH_UNSET_BACKREF
.sp
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 (\e1)(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).
.sp
  PCRE2_MULTILINE
.sp
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_DOLLAR_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.
.P
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 newlines in a subject string, or no
occurrences of ^ or $ in a pattern, setting PCRE2_MULTILINE has no effect.
.sp
  PCRE2_NEVER_UCP
.sp
This option locks out the use of Unicode properties for handling \eB, \eb, \eD,
\ed, \eS, \es, \eW, \ew, 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 PCRE_NEVER_UCP causes an error.
.sp
  PCRE2_NEVER_UTF
.sp
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 prevents 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.
.sp
  PCRE2_NO_AUTO_CAPTURE
.sp
If this option is set, it disables the use of numbered capturing parentheses 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.
.sp
  PCRE2_NO_AUTO_POSSESS
.sp
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 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 provided for testing
purposes.
.sp
  PCRE2_NO_START_OPTIMIZE
.sp
This is an option whose main effect is at matching time. It does not change
what \fBpcre2_compile()\fP generates, but it does affect the output of the JIT
compiler.
.P
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 immediately if it cannot find it, without
actually running the main matching 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 optimizations are
in effect a pre-scan of the subject that takes place before the pattern is run.
.P
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 such as (*COMMIT)
and (*MARK) are considered at every possible starting position in the subject
string.
.P
Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching operation.
Consider the pattern
.sp
  (*COMMIT)ABC
.sp
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 pattern 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
.sp
  (*MARK:A)(X|Y)
.sp
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 affect the overall match result, which is still
"no match", but it does affect the auxiliary information that is returned.
.sp
  PCRE2_NO_UTF_CHECK
.sp
When PCRE2_UTF is set, the validity of the pattern as a UTF string is
automatically checked. There are discussions about the validity of
.\" HTML <a href="pcre2unicode.html#utf8strings">
.\" </a>
UTF-8 strings,
.\"
.\" HTML <a href="pcre2unicode.html#utf16strings">
.\" </a>
UTF-16 strings,
.\"
and
.\" HTML <a href="pcre2unicode.html#utf32strings">
.\" </a>
UTF-32 strings
.\"
in the
.\" HREF
\fBpcre2unicode\fP
.\"
document. 
If an invalid UTF sequence is found, \fBpcre2_compile()\fP returns a negative
error code.
.P
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 pattern is undefined. It may
cause your program to crash or loop. Note that this option can also be passed
to \fBpcre2_match()\fP and \fBpcre_dfa_match()\fP, to suppress validity
checking of the subject string.
.sp
  PCRE2_UCP
.sp
This option changes the way PCRE2 processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
\ew, 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
.\" HTML <a href="pcre2.html#genericchartypes">
.\" </a>
generic character types
.\"
in the
.\" HREF
\fBpcre2pattern\fP
.\"
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.
.sp
  PCRE2_UNGREEDY
.sp
This option inverts the "greediness" of the quantifiers so that they are not
greedy by default, but become greedy if followed by "?". It is not compatible
with Perl. It can also be set by a (?U) option setting within the pattern.
.sp
  PCRE2_UTF
.sp
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
.\" HREF
\fBpcre2unicode\fP
.\"
page.
.
.
.SH "COMPILATION ERROR CODES"
.rs
.sp
There are over 80 positive error codes that \fBpcre2_compile()\fP 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
\fBpcre2_match()\fP and \fBpcre2_dfa_match()\fP, and are described in the
.\" HREF
\fBpcre2unicode\fP
.\"
page. The \fBpcre2_get_error_message()\fP function can be called to obtain a
textual error message from any error code.
.
.
.SH "JUST-IN-TIME (JIT) COMPILATION"
.rs
.sp
.nf
.B int pcre2_jit_compile(pcre2_code *\fIcode\fP, uint32_t \fIoptions\fP);
.sp
.B int pcre2_jit_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
.B "  pcre2_match_context *\fImcontext\fP, pcre2_jit_stack *\fIjit_stack\fP);"
.sp
.B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP);
.sp
.B pcre2_jit_stack *pcre2_jit_stack_alloc(pcre2_general_context *\fIgcontext\fP,
.B "  PCRE2_SIZE \fIstartsize\fP, PCRE2_SIZE \fImaxsize\fP);"
.sp
.B void pcre2_jit_stack_assign(const pcre2_code *\fIcode\fP,
.B "  pcre2_jit_callback \fIcallback_function\fP, void *\fIcallback_data\fP);"
.sp
.B void pcre2_jit_stack_free(pcre2_jit_stack *\fIjit_stack\fP);
.fi
.P
These functions provide support for JIT compilation, which, if the just-in-time
compiler is available, further processes a compiled pattern into machine code
that executes much faster than the \fBpcre2_match()\fP interpretive matching
function. Full details are given in the
.\" HREF
\fBpcre2jit\fP
.\"
documentation.
.P
JIT compilation is a heavyweight optimization. It can take some time for
patterns to be analyzed, and for one-off matches and simple patterns 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.
.
.
.\" HTML <a name="localesupport"></a>
.SH "LOCALE SUPPORT"
.rs
.sp
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 \ew or \ed. However, if
PCRE2 is built with UTF support, all characters can be tested with \ep and \eP,
or, alternatively, the PCRE2_UCP option can be set when a pattern is compiled;
this causes \ew and friends to use Unicode property support instead of the
built-in tables.
.P
The use of locales with Unicode is discouraged. If you are handling characters
with code points greater than 128, you should either use Unicode support, or
use locales, but not try to mix the two.
.P
PCRE2 contains an internal set of character tables that are used by default.
These are sufficient for many applications. Normally, the internal tables
recognize only ASCII characters. However, when PCRE2 is built, it is possible
to cause the internal tables to be rebuilt in the default "C" locale of the
local system, which may cause them to be different.
.P
The internal tables can be overridden by tables supplied by the application
that calls PCRE2. These may be created in a different locale from the default.
As more and more applications change to using Unicode, the need for this locale
support is expected to die away.
.P
External tables are built by calling the \fBpcre2_maketables()\fP function, in
the relevant locale. The result can be passed to \fBpcre2_compile()\fP as often
as necessary, by creating a compile context and calling
\fBpcre2_set_character_tables()\fP to set the tables pointer therein. For
example, to build and use tables that are appropriate for the French locale
(where accented characters with values greater than 128 are treated as
letters), the following code could be used:
.sp
  setlocale(LC_CTYPE, "fr_FR");
  tables = pcre2_maketables(NULL);
  ccontext = pcre2_compile_context_create(NULL);
  pcre2_set_character_tables(ccontext, tables);
  re = pcre2_compile(..., ccontext);
.sp
The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
are using Windows, the name for the French locale is "french". It is the
caller's responsibility to ensure that the memory containing the tables remains
available for as long as it is needed.
.P
The pointer that is passed (via the compile context) to \fBpcre2_compile()\fP
is saved with the compiled pattern, and the same tables are used by
\fBpcre2_match()\fP and \fBpcre_dfa_match()\fP. Thus, for any single pattern,
compilation, and matching all happen in the same locale, but different patterns
can be processed in different locales.
.
.
.\" HTML <a name="infoaboutpattern"></a>
.SH "INFORMATION ABOUT A COMPILED PATTERN"
.rs
.sp
.nf
.B int pcre2_pattern_info(const pcre2 *\fIcode\fP, uint32_t \fIwhat\fP, void *\fIwhere\fP);
.fi
.P
The \fBpcre2_pattern_info()\fP function returns information about a compiled
pattern. The first argument is a pointer to the compiled pattern. The second
argument specifies which piece of information is required, and the third
argument is a pointer to a variable to receive the data. The yield of the
function is zero for success, or one of the following negative numbers:
.sp
  PCRE2_ERROR_NULL           the argument \fIcode\fP was NULL
                             the argument \fIwhere\fP was NULL
  PCRE2_ERROR_BADMAGIC       the "magic number" was not found
  PCRE2_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
  PCRE2_ERROR_UNSET          the requested field is not set
.sp
The "magic number" is placed at the start of each compiled pattern as an simple
check against passing an arbitrary memory pointer.
Here is
a typical call of \fBpcre2_pattern_info()\fP, to obtain the length of the compiled
pattern:
.sp
  int rc;
  size_t length;
  rc = pcre2_pattern_info(
    re,               /* result of pcre2_compile() */
    PCRE2_INFO_SIZE,  /* what is required */
    &length);         /* where to put the data */
.sp
The possible values for the second argument are defined in \fBpcre2.h\fP, and
are as follows:
.sp
  PCRE2_INFO_ALLOPTIONS
  PCRE2_INFO_ARGOPTIONS 
.sp
Return a copy of the pattern's options. The third argument should point to a 
\fBuint32_t\fP variable. PCRE2_INFO_ARGOPTIONS returns exactly the options that
were passed to \fBpcre2_compile()\fP, whereas PCRE2_INFO_ALLOPTIONS returns
the compile options as modified by any top-level option settings at the start
of the pattern itself. In other words, they are the options that will be in
force when matching starts. For example, if the pattern /(?im)abc(?-i)d/ is
compiled with the PCRE2_EXTENDED option, the result is PCRE2_CASELESS,
PCRE2_MULTILINE, and PCRE2_EXTENDED.
.P
A pattern is automatically anchored by PCRE2 if all of its top-level
alternatives begin with one of the following:
.sp
  ^     unless PCRE2_MULTILINE is set
  \eA    always
  \eG    always
.\" JOIN
  .*    if PCRE2_DOTALL is set and there are no back
          references to the subpattern in which .* appears
.sp
For such patterns, the PCRE2_ANCHORED bit is set in the options returned for 
PCRE2_INFO_ALLOPTIONS.
.sp
  PCRE2_INFO_BACKREFMAX
.sp
Return the number of the highest back reference in the pattern. The third
argument should point to an \fBuint32_t\fP variable. Zero is returned if there
are no back references.
.sp
  PCRE2_INFO_BSR
.sp
The output is a uint32_t whose value indicates what character sequences the \eR
escape sequence matches by default. A value of 0 means that \eR matches any
Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
or CRLF. The default can be overridden when a pattern is matched.
.sp
  PCRE2_INFO_CAPTURECOUNT
.sp
Return the number of capturing subpatterns in the pattern. The third argument
should point to an \fBuint32_t\fP variable.
.sp
  PCRE2_INFO_FIRSTCODETYPE
.sp
Return information about the first code unit of any matched string, for a
non-anchored pattern. The third argument should point to an \fBuint32_t\fP
variable.
.P
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
.sp
(a) the pattern was compiled with the PCRE2_MULTILINE option, and every branch
starts with "^", or
.sp
(b) every branch of the pattern starts with ".*" and PCRE2_DOTALL is not set
(if it were set, the pattern would be anchored),
.sp
2 is returned, indicating that the pattern matches only at the start of a
subject string or after any newline within the string. Otherwise 0 is
returned. For anchored patterns, 0 is returned.
.sp
  PCRE2_INFO_FIRSTCODEUNIT
.sp
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 \fBuint32_t\fP 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.
.sp
  PCRE2_INFO_FIRSTBITMAP
.sp
In the absence of a single first code unit for a non-anchored pattern,
\fBpcre2_compile()\fP 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 constructed, a pointer to it is
returned. Otherwise NULL is returned. The third argument should point to an
\fBconst uint8_t *\fP variable.
.sp
  PCRE2_INFO_HASCRORLF
.sp
Return 1 if the pattern contains any explicit matches for CR or LF characters,
otherwise 0. The third argument should point to an \fBuint32_t\fP variable. An
explicit match is either a literal CR or LF character, or \er or \en.
.sp
  PCRE2_INFO_JCHANGED
.sp
Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
0. The third argument should point to an \fBuint32_t\fP variable. (?J) and
(?-J) set and unset the local PCRE2_DUPNAMES option, respectively.
.sp
  PCRE2_INFO_JITSIZE
.sp
If the compiled pattern was successfully processed by
\fBpcre2_jit_compile()\fP, return the size of the JIT compiled code, otherwise
return zero. The third argument should point to a \fBsize_t\fP variable.
.sp
  PCRE2_INFO_LASTCODETYPE
.sp
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
\fBuint32_t\fP 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.
.P
For anchored patterns, a last literal value is recorded only if it follows
something of variable length. For example, for the pattern /^a\ed+z\ed+/ the
returned value is 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for
/^a\edz\ed/ the returned value is 0.
.sp
  PCRE2_INFO_LASTCODEUNIT
.sp
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 \fBuint32_t\fP variable. If there is no such
value, 0 is returned.
.sp
  PCRE2_INFO_MATCHEMPTY
.sp
Return 1 if the pattern can match an empty string, otherwise 0. The third
argument should point to an \fBuint32_t\fP variable.
.sp
  PCRE2_INFO_MATCHLIMIT
.sp
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 \fBpcre2_pattern_info()\fP returns the error PCRE2_ERROR_UNSET.
.sp
  PCRE2_INFO_MAXLOOKBEHIND
.sp
Return the number of characters (not code units) in the longest lookbehind
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 \eb and \eB
require a one-character lookbehind. \eA 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 processed. Otherwise, if there are no lookbehinds in the
pattern, \eA might match incorrectly at the start of a new segment.
.sp
  PCRE2_INFO_MINLENGTH
.sp
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 number of code units.
The third argument should point to an \fBuint32_t\fP 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.
.sp
  PCRE2_INFO_NAMECOUNT
  PCRE2_INFO_NAMEENTRYSIZE
  PCRE2_INFO_NAMETABLE
.sp
PCRE2 supports the use of named as well as numbered capturing parentheses. The
names are just an additional way of identifying the parentheses, which still
acquire numbers. Several convenience functions such as
\fBpcre2_substring_get_byname()\fP are provided for extracting captured
substrings 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 \fBpcre2_match()\fP below). To do the conversion,
you need to use the name-to-number map, which is described by these three
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.
.P
The names are in alphabetical order. If (?| is used to create multiple groups
with the same number, as described in the
.\" HTML <a href="pcre2pattern.html#dupsubpatternnumber">
.\" </a>
section on duplicate subpattern numbers
.\"
in the
.\" HREF
\fBpcre2pattern\fP
.\"
page, the groups may be given the same name, but there is only one entry in the
table. Different names for groups of the same number are not permitted.
.P
Duplicate names for subpatterns with different numbers are permitted, but only
if PCRE2_DUPNAMES is set. They appear in the table in the order in which they
were found in the pattern. In the absence of (?| this is the order of
increasing number; when (?| is used this is not necessarily the case because
later subpatterns may have lower numbers.
.P
As a simple example of the name/number table, consider the following pattern
after compilation by the 8-bit library (assume PCRE2_EXTENDED is set, so white
space - including newlines - is ignored):
.sp
.\" JOIN
  (?<date> (?<year>(\ed\ed)?\ed\ed) -
  (?<month>\ed\ed) - (?<day>\ed\ed) )
.sp
There are four named subpatterns, so the table has four entries, and each entry
in the table is eight bytes long. The table is as follows, with non-printing
bytes shows in hexadecimal, and undefined bytes shown as ??:
.sp
  00 01 d  a  t  e  00 ??
  00 05 d  a  y  00 ?? ??
  00 04 m  o  n  t  h  00
  00 02 y  e  a  r  00 ??
.sp
When writing code to extract data from named subpatterns using the
name-to-number map, remember that the length of the entries is likely to be
different for each compiled pattern.
.sp
  PCRE2_INFO_NEWLINE
.sp
The output is a \fBuint32_t\fP whose value specifies the default character
sequence that will be recognized as meaning "newline" while matching. The
values are:
.sp
  1  Carriage return (CR)
  2  Linefeed (LF)
  3  Carriage return, linefeed (CRLF)
  4  Any Unicode line ending
  5  Any of CR, LF, or CRLF
.sp       
The default can be overridden when a pattern is matched.
.sp
  PCRE2_INFO_RECURSIONLIMIT
.sp
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 \fBpcre2_pattern_info()\fP returns the error PCRE2_ERROR_UNSET.
.sp
  PCRE2_INFO_SIZE
.sp
Return the size of the compiled pattern in bytes (for all three libraries). The
third argument should point to a \fBsize_t\fP variable. This value does not
include the size of the \fBpcre2_code\fP structure that is returned by
\fBpcre_compile()\fP. The value that is used when \fBpcre2_compile()\fP is
getting memory in which to place the compiled data is the value returned by
this option plus the size of the \fBpcre2_code\fP structure. Processing a
pattern with the JIT compiler does not alter the value returned by this option.
.
.
.\" HTML <a name="matchdatablock"></a>
.SH "THE MATCH DATA BLOCK"
.rs
.sp
.nf
.B pcre2_match_data_create(uint32_t \fIovecsize\fP,
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B pcre2_match_data_create_from_pattern(pcre2_code *\fIcode\fP,
.B "  pcre2_general_context *\fIgcontext\fP);"
.sp
.B void pcre2_match_data_free(pcre2_match_data *\fImatch_data\fP);
.fi
.P
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 \fIovector\fP. 
.P
Before calling \fBpcre2_match()\fP or \fBpcre2_dfa_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 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 \fBpcre2_match_data_create()\fP, so it is always possible to
return the overall matched string.
.P
For \fBpcre2_match_data_create_from_pattern()\fP, 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.
.P
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 management, pass NULL.
.P
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
\fBpcre2_match_data_free()\fP. How to extract information from a match data
block after a match operation is described in the sections on
.\" HTML <a href="#matchedstrings">
.\" </a>
matched strings
.\"
and
.\" HTML <a href="#matchotherdata">
.\" </a>
other match data
.\"
below.
.
.
.SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
.rs
.sp
.nf
.B int pcre2_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
.B "  pcre2_match_context *\fImcontext\fP);"
.fi
.P
The function \fBpcre2_match()\fP is called to match a subject string against a
compiled pattern, which is passed in the \fIcode\fP argument. You can call
\fBpcre2_match()\fP with the same \fIcode\fP argument as many times as you
like, in order to find multiple matches in the subject string or to match
different subject strings with the same pattern.
.P
This function is the main matching facility of the library, and it operates in
a Perl-like manner. For specialist use there is also an alternative matching
function, which is described
.\" HTML <a href="#dfamatch">
.\" </a>
below
.\"
in the section about the \fBpcre2_dfa_match()\fP function.
.P
Here is an example of a simple call to \fBpcre2_match()\fP:
.sp
  pcre2_match_data *md = pcre2_match_data_create(4, NULL);
  int rc = pcre2_match(
    re,             /* result of pcre2_compile() */
    "some string",  /* the subject string */
    11,             /* the length of the subject string */
    0,              /* start at offset 0 in the subject */
    0,              /* default options */
    match_data,     /* the match data block */
    NULL);          /* a match context; NULL means use defaults */
.sp
If the subject string is zero-terminated, the length can be given as 
PCRE2_ZERO_TERMINATED. A match context must be provided if certain less common 
matching parameters are to be changed. For details, see the section on
.\" HTML <a href="#matchcontext">
.\" </a>
the match context
.\"
above.
.
.
.SS "The string to be matched by \fBpcre2_match()\fP"
.rs
.sp
The subject string is passed to \fBpcre2_match()\fP as a pointer in
\fIsubject\fP, a length in \fIlength\fP, and a starting offset in
\fIstartoffset\fP. The length and offset are in code units, not characters.
That is, they are in bytes for the 8-bit library, 16-bit code units for the
16-bit library, and 32-bit code units for the 32-bit library, whether or not 
UTF processing is enabled.
.P
If \fIstartoffset\fP is greater than the length of the subject,
\fBpcre2_match()\fP returns PCRE2_ERROR_BADOFFSET. When the starting offset is
zero, the search for a match starts at the beginning of the subject, and this
is by far the most common case. In UTF-8 or UTF-16 mode, the starting offset
must point to the start of a character, or to the end of the subject (in UTF-32
mode, one code unit equals one character, so all offsets are valid). Like the
pattern string, the subject may contain binary zeroes. 
.P
A non-zero starting offset is useful when searching for another match in the
same subject by calling \fBpcre2_match()\fP again after a previous success.
Setting \fIstartoffset\fP differs from passing over a shortened string and
setting PCRE2_NOTBOL in the case of a pattern that begins with any kind of
lookbehind. For example, consider the pattern
.sp
  \eBiss\eB
.sp
which finds occurrences of "iss" in the middle of words. (\eB matches only if
the current position in the subject is not a word boundary.) When applied to
the string "Mississipi" the first call to \fBpcre2_match()\fP finds the first
occurrence. If \fBpcre2_match()\fP is called again with just the remainder of
the subject, namely "issipi", it does not match, because \eB is always false at
the start of the subject, which is deemed to be a word boundary. However, if
\fBpcre2_match()\fP is passed the entire string again, but with
\fIstartoffset\fP set to 4, it finds the second occurrence of "iss" because it
is able to look behind the starting point to discover that it is preceded by a
letter.
.P
Finding all the matches in a subject is tricky when the pattern can match an
empty string. It is possible to emulate Perl's /g behaviour by first trying the
match again at the same offset, with the PCRE2_NOTEMPTY_ATSTART and
PCRE2_ANCHORED options, and then if that fails, advancing the starting offset
and trying an ordinary match again. There is some code that demonstrates how to
do this in the
.\" HREF
\fBpcre2demo\fP
.\"
sample program. In the most general case, you have to check to see if the
newline convention recognizes CRLF as a newline, and if so, and the current
character is CR followed by LF, advance the starting offset by two characters
instead of one.
.P
If a non-zero starting offset is passed when the pattern is anchored, one
attempt to match at the given offset is made. This can only succeed if the
pattern does not require the match to be at the start of the subject.
.
.
.\" HTML <a name="matchoptions"></a>
.SS "Option bits for \fBpcre2_match()\fP"
.rs
.sp
The unused bits of the \fIoptions\fP argument for \fBpcre2_match()\fP 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, and PCRE2_PARTIAL_SOFT. Their action is described below.
.P
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
\fBpcre2_match()\fP is run.
.sp
  PCRE2_ANCHORED
.sp
The PCRE2_ANCHORED option limits \fBpcre2_match()\fP to matching at the first
matching position. If a pattern was compiled with PCRE2_ANCHORED, or turned out
to be anchored by virtue of its contents, it cannot be made unachored at
matching time. Note that setting the option at match time disables JIT 
matching.
.sp
  PCRE2_NOTBOL
.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.
.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.
.sp
  PCRE2_NOTEMPTY
.sp
An empty string is not considered to be a valid match if this option is set. If
there are alternatives in the pattern, they are tried. If all the alternatives
match the empty string, the entire match fails. For example, if the pattern
.sp
  a?b?
.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".
.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.
.sp
  PCRE2_NO_UTF_CHECK
.sp
When PCRE2_UTF is set at compile time, the validity of the subject as a UTF
string is checked by default when \fBpcre2_match()\fP is subsequently called.
The entire string is checked before any other processing takes place, and a
negative error code is returned if the check fails. There are several UTF error
codes for each code unit width, corresponding to different problems with the
code unit sequence. The value of \fIstartoffset\fP is also checked, to ensure
that it points to the start of a character or to the end of the subject. There
are discussions about the validity of
.\" HTML <a href="pcre2unicode.html#utf8strings">
.\" </a>
UTF-8 strings,
.\"
.\" HTML <a href="pcre2unicode.html#utf16strings">
.\" </a>
UTF-16 strings,
.\"
and
.\" HTML <a href="pcre2unicode.html#utf32strings">
.\" </a>
UTF-32 strings
.\"
in the
.\" HREF
\fBpcre2unicode\fP
.\"
page. 
.P
If you know that your subject is valid, and you want to skip these checks for
performance reasons, you can set the PCRE2_NO_UTF_CHECK option when calling
\fBpcre2_match()\fP. You might want to do this for the second and subsequent
calls to \fBpcre2_match()\fP if you are making repeated calls to find all the
matches in a single subject string. 
.P
NOTE: When PCRE2_NO_UTF_CHECK is set, the effect of passing an invalid string
as a subject, or an invalid value of \fIstartoffset\fP, is undefined. Your
program may crash or loop indefinitely.
.sp
  PCRE2_PARTIAL_HARD
  PCRE2_PARTIAL_SOFT
.sp
These options turn on the partial matching feature. A partial match occurs if
the end of the subject string is reached successfully, but there are not enough
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.
.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
PCRE2_ERROR_PARTIAL, without considering any other alternatives. In other
words, when PCRE2_PARTIAL_HARD is set, a partial match is considered to be more
important that an alternative complete match.
.P
There is a more detailed discussion of partial and multi-segment matching, with
examples, in the
.\" HREF
\fBpcre2partial\fP
.\"
documentation.
.
.
.
.SH "NEWLINE HANDLING WHEN MATCHING"
.rs
.sp 
When PCRE2 is built, a default newline convention is set; this is usually the 
standard convention for the operating system. The default can be overridden in 
either a 
.\" HTML <a href="#compilecontext">
.\" </a>
compile context
.\"
or a
.\" HTML <a href="#matchcontext">
.\" </a>
match context.
.\"
However, changing the newline convention at match time disables JIT matching.
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.
.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.
.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
not set), it does not match the string "\er\enA" because, after failing at the
start, it skips both the CR and the LF before retrying. However, the pattern
[\er\en]A does match that string, because it contains an explicit CR or LF
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).
.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.
.
.
.\" HTML <a name="matchedstrings"></a>
.SH "HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS"
.rs
.sp
.nf
.B uint32_t pcre2_get_ovector_count(pcre2_match_data *\fImatch_data\fP);
.sp
.B PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *\fImatch_data\fP);
.fi
.P
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.
.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
.\" HTML <a href="#matchdatablock">
.\" </a>
match data block.
.\"
You can obtain direct access to the ovector by calling 
\fBpcre2_get_ovector_pointer()\fP to find its address, and 
\fBpcre2_get_ovector_count()\fP to find the number of pairs of values it
contains. Alternatively, you can use the auxiliary functions for accessing
captured substrings
.\" HTML <a href="#extractbynumber">
.\" </a>
by number
.\"
or
.\" HTML <a href="#extractbyname">
.\" </a>
by name
.\"
(see below).
.P
Within the ovector, the first in each pair of values is set to the offset 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 values 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.
.P
The first pair of offsets (that is, \fIovector[0]\fP and \fIovector[1]\fP)
identifies 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 \fBpcre2_match()\fP is one more than the highest 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.
.P
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.
.P
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, \fBpcre2_match()\fP 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 \fIovector\fP is not big enough to
remember the related substrings, PCRE2 has to get additional memory for use
during matching. Thus it is usually advisable to set up a match data block
containing an ovector of reasonable size.
.P
It is possible for capturing subpattern number \fIn+1\fP to match some part of
the subject when subpattern \fIn\fP has not been used at all. For example, 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 corresponding to unused subpatterns
are set to PCRE2_UNSET.
.P
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 highest used capturing
subpattern number is 1. The offsets for for the second and third capturing
subpatterns (assuming the vector is large enough, of course) are set to
PCRE2_UNSET.
.P
Elements in the ovector that do not correspond to capturing parentheses in the
pattern are never changed. That is, if a pattern contains \fIn\fP capturing
parentheses, no more than \fIovector[0]\fP to \fIovector[2n+1]\fP are set by
\fBpcre2_match()\fP. The other elements retain whatever values they previously
had.
.
.
.\" HTML <a name="matchotherdata"></a>
.SS "Other information about the match"
.rs
.sp
.nf
.B PCRE2_SPTR pcre2_get_mark(pcre2_match_data *\fImatch_data\fP);
.sp
.B PCRE2_SIZE pcre2_get_leftchar(pcre2_match_data *\fImatch_data\fP);
.sp
.B PCRE2_SIZE pcre2_get_rightchar(pcre2_match_data *\fImatch_data\fP);
.sp
.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 
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
pointer to the zero-terminated name, which is within the compiled pattern. 
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.
.P
The other three functions yield values that give information about the part of 
the subject string that was inspected during a successful match or a partial 
match. Their results are undefined after a failed match. They return the 
following values, respectively:
.sp
(1) The offset of the leftmost character that was inspected during the match.
This can be earlier than the point at which the match started if the pattern
contains lookbehind assertions or \eb or \eB at the start.
.sp
(2) The offset of the character that follows the rightmost character that was
inspected during the match. This can be after the end of the match if the 
pattern contains lookahead assertions.
.sp
(3) The offset of the character at which the successful or partial match 
started. This can be different to the value of \fIovector[0]\fP if the pattern 
contains the \eK escape sequence.
.P
For example, if the pattern (?<=abc)xx\eKyy(?=def) is matched against the
string "123abcxxyydef123", the resulting offsets are:
.sp
  ovector[0]   8
  ovector[1]  10
  leftchar     3
  rightchar   13
  startchar    6
.sp
The \fBallusedtext\fP modifier in \fBpcre2test\fP can be used to display a
longer string that shows the leftmost and rightmost characters in a match
instead of just the matched string.
.
.
.\" HTML <a name="errorlist"></a>
.SS "Error return values from \fBpcre2_match()\fP"
.rs
.sp
If \fBpcre2_match()\fP fails, it returns a negative number. This can be 
converted to a text string by calling \fBpcre2_get_error_message()\fP. 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 checking 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 given in the
.\" HREF
\fBpcre2unicode\fP
.\"
page. The following are the other errors that may be returned by
\fBpcre2_match()\fP:
.sp
  PCRE2_ERROR_NOMATCH
.sp
The subject string did not match the pattern.
.sp
  PCRE2_ERROR_PARTIAL
.sp
The subject string did not match, but it did match partially. See the
.\" HREF
\fBpcre2partial\fP
.\"
documentation for details of partial matching.
.sp
  PCRE2_ERROR_BADMAGIC
.sp
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 that is
returned when the magic number is not present.
.sp
  PCRE2_ERROR_BADMODE
.sp
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.
.sp
  PCRE2_ERROR_BADOFFSET
.sp
The value of \fIstartoffset\fP greater than the length of the subject.
.sp
  PCRE2_ERROR_BADOPTION
.sp
An unrecognized bit was set in the \fIoptions\fP argument.
.sp
  PCRE2_ERROR_BADUTFOFFSET
.sp
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
\fIstartoffset\fP did not point to the beginning of a UTF character or the end
of the subject.
.sp
  PCRE2_ERROR_CALLOUT
.sp
This error is never generated by \fBpcre2_match()\fP itself. It is provided for
use by callout functions that want to cause \fBpcre2_match()\fP to return a
distinctive error code. See the
.\" HREF
\fBpcre2callout\fP
.\"
documentation for details.
.sp
  PCRE2_ERROR_INTERNAL
.sp
An unexpected internal error has occurred. This error could be caused by a bug
in PCRE2 or by overwriting of the compiled pattern.
.sp
  PCRE2_ERROR_JIT_BADOPTION
.sp
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
.\" HREF
\fBpcre2jit\fP
.\"
documentation for more details.
.sp
  PCRE2_ERROR_JIT_STACKLIMIT
.sp
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
.\" HREF
\fBpcre2jit\fP
.\"
documentation for more details.
.sp
  PCRE2_ERROR_MATCHLIMIT
.sp
The backtracking limit was reached.
.sp
  PCRE2_ERROR_NOMEMORY
.sp
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 error is given when memory cannot
be obtained.
.sp
  PCRE2_ERROR_NULL
.sp
Either the \fIcode\fP, \fIsubject\fP, or \fImatch_data\fP argument was passed
as NULL.
.sp
  PCRE2_ERROR_RECURSELOOP
.sp
This error is returned when \fBpcre2_match()\fP detects a recursion loop within
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.
.sp
  PCRE2_ERROR_RECURSIONLIMIT
.sp
The internal recursion limit was reached.
.
.
.\" HTML <a name="extractbynumber"></a>
.SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
.rs
.sp
.nf
.B int pcre2_substring_length_bynumber(pcre2_match_data *\fImatch_data\fP,
.B "  unsigned int \fInumber\fP, PCRE2_SIZE *\fIlength\fP);"
.sp
.B int pcre2_substring_copy_bynumber(pcre2_match_data *\fImatch_data\fP,
.B "  unsigned int \fInumber\fP, PCRE2_UCHAR *\fIbuffer\fP,"
.B "  PCRE2_SIZE *\fIbufflen\fP);"
.sp
.B int pcre2_substring_get_bynumber(pcre2_match_data *\fImatch_data\fP,
.B "  unsigned int \fInumber\fP, PCRE2_UCHAR **\fIbufferptr\fP,"
.B "  PCRE2_SIZE *\fIbufflen\fP);"
.sp
.B void pcre2_substring_free(PCRE2_UCHAR *\fIbuffer\fP);
.fi
.P
Captured substrings can be accessed directly by using the ovector as described
.\" HTML <a href="#matchedstrings">
.\" </a>
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 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 course, a C string.
.P
You can find the length in code units of a captured substring without
extracting it by calling \fBpcre2_substring_length_bynumber()\fP. 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.
.P
The \fBpcre2_substring_copy_bynumber()\fP function copies one string into a 
supplied buffer, whereas \fBpcre2_substring_get_bynumber()\fP 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 functions are a
pointer to the match data block and a capturing group number. A group number of
zero extracts the substring that matched the entire pattern, and higher values
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.
.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 
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 \fBpcre2_substring_free()\fP.
.P
The return value from these functions is zero for success, or one of these
error codes:
.sp
  PCRE2_ERROR_NOMEMORY
.sp
The buffer was too small for \fBpcre2_substring_copy_bynumber()\fP, or the
attempt to get memory failed for \fBpcre2_substring_get_bynumber()\fP.
.sp
  PCRE2_ERROR_NOSUBSTRING
.sp
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.
.
.
.SH "EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS"
.rs
.sp
.nf
.B int pcre2_substring_list_get(pcre2_match_data *\fImatch_data\fP,
.B "  PCRE2_UCHAR ***\fIlistptr\fP, PCRE2_SIZE **\fIlengthsptr\fP);
.sp
.B void pcre2_substring_list_free(PCRE2_SPTR *\fIlist\fP);
.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.
.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
NULL pointer. The address of the list of lengths is returned via
\fIlengthsptr\fP. If your strings do not contain binary zeros and you do not
therefore need the lengths, you may supply NULL as the \fBlengthsptr\fP
argument 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 memory block
could not be obtained. When the list is no longer needed, it should be freed by 
calling \fBpcre2_substring_list_free()\fP.
.P
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
substrings.
.
.
.\" HTML <a name="extractbynname"></a>
.SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
.rs
.sp
.nf
.B int pcre2_substring_number_from_name(const pcre2_code *\fIcode\fP,
.B "  PCRE2_SPTR \fIname\fP);"
.sp
.B int pcre2_substring_length_byname(pcre2_match_data *\fImatch_data\fP,
.B "  PCRE2_SPTR \fIname\fP, PCRE2_SIZE *\fIlength\fP);"
.sp
.B int pcre2_substring_copy_byname(pcre2_match_data *\fImatch_data\fP,
.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR *\fIbuffer\fP, PCRE2_SIZE *\fIbufflen\fP);"
.sp
.B int pcre2_substring_get_byname(pcre2_match_data *\fImatch_data\fP,
.B "  PCRE2_SPTR \fIname\fP, PCRE2_UCHAR **\fIbufferptr\fP, PCRE2_SIZE *\fIbufflen\fP);"
.sp
.B void pcre2_substring_free(PCRE2_UCHAR *\fIbuffer\fP);
.fi
.P
To extract a substring by name, you first have to find associated number.
For example, for this pattern:
.sp
  (a+)b(?<xxx>\ed+)...
.sp
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 the name by
calling \fBpcre2_substring_number_from_name()\fP. The first argument is the
compiled pattern, and the second is the name. The yield of the function is the
subpattern number, or PCRE2_ERROR_NOSUBSTRING if there is no 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).
.P
\fBWarning:\fP If the pattern uses the (?| feature to set up multiple
subpatterns with the same number, as described in the
.\" HTML <a href="pcre2pattern.html#dupsubpatternnumber">
.\" </a>
section on duplicate subpattern numbers
.\"
in the
.\" HREF
\fBpcre2pattern\fP
.\"
page, you cannot use names to distinguish the different subpatterns, because
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.
.
.
.SH "DUPLICATE SUBPATTERN NAMES"
.rs
.sp
.nf
.B int pcre2_substring_nametable_scan(const pcre2_code *\fIcode\fP,
.B "  PCRE2_SPTR \fIname\fP, PCRE2_SPTR *\fIfirst\fP, PCRE2_SPTR *\fIlast\fP);"
.fi
.P
When a pattern is compiled with the PCRE2_DUPNAMES option, names for
subpatterns are not required to be unique. Duplicate names are always allowed
for subpatterns with the same number, created by using the (?| feature. Indeed,
if such subpatterns are named, they are required to use the same names.
.P
Normally, patterns with duplicate names are such that in any one match, only
one of the named subpatterns participates. An example is shown in the
.\" HREF
\fBpcre2pattern\fP
.\"
documentation.
.P
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.
.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
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.
.P
The format of the name table is described above in the section entitled
\fIInformation about a pattern\fP
.\" HTML <a href="#infoaboutpattern">
.\" </a>
above.
.\"
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"
.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
.\" HREF
\fBpcre2callout\fP
.\"
documentation.
.P
What you have to do is to insert a callout right at the end of the pattern.
When your callout function is called, extract and save the current matched
substring. Then return 1, which forces \fBpcre2_match()\fP to backtrack and try
other alternatives. Ultimately, when it runs out of matches,
\fBpcre2_match()\fP will yield PCRE2_ERROR_NOMATCH.
.
.
.\" HTML <a name="dfamatch"></a>
.SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
.rs
.sp
.nf
.B int pcre2_dfa_match(const pcre2_code *\fIcode\fP, PCRE2_SPTR \fIsubject\fP,
.B "  PCRE2_SIZE \fIlength\fP, PCRE2_SIZE \fIstartoffset\fP,"
.B "  uint32_t \fIoptions\fP, pcre2_match_data *\fImatch_data\fP,"
.B "  pcre2_match_context *\fImcontext\fP,"
.B "  int *\fIworkspace\fP, PCRE2_SIZE \fIwscount\fP);"
.fi
.P
The function \fBpcre2_dfa_match()\fP 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. Nevertheless, 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 \fBpcre2_dfa_match()\fP does not support, see the
.\" HREF
\fBpcre2matching\fP
.\"
documentation.
.P
The arguments for the \fBpcre2_dfa_match()\fP function are the same as for
\fBpcre2_match()\fP, plus two extras. The ovector within the match data block
is used in a different way, and this is described below. The other common
arguments are used in the same way as for \fBpcre2_match()\fP, so their
description is not repeated here.
.P
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 potential matches.
.P
Here is an example of a simple call to \fBpcre2_dfa_match()\fP:
.sp
  int wspace[20];
  pcre2_match_data *md = pcre2_match_data_create(4, NULL);
  int rc = pcre2_dfa_match(
    re,             /* result of pcre2_compile() */
    "some string",  /* the subject string */
    11,             /* the length of the subject string */
    0,              /* start at offset 0 in the subject */
    0,              /* default options */
    match_data,     /* the match data block */
    NULL,           /* a match context; NULL means use defaults */
    wspace,         /* working space vector */
    20);            /* number of elements (NOT size in bytes) */
.
.SS "Option bits for \fBpcre_dfa_match()\fP"
.rs
.sp
The unused bits of the \fIoptions\fP argument for \fBpcre2_dfa_match()\fP 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
\fBpcre2_match()\fP, so their description is not repeated here.
.sp
  PCRE2_PARTIAL_HARD
  PCRE2_PARTIAL_SOFT
.sp
These have the same general effect as they do for \fBpcre2_match()\fP, but the
details are slightly different. When PCRE2_PARTIAL_HARD is set for
\fBpcre2_dfa_match()\fP, 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, but there is still at
least one matching possibility. The portion 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 examples, in the
.\" HREF
\fBpcre2partial\fP
.\"
documentation.
.sp
  PCRE2_DFA_SHORTEST
.sp
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 alternative algorithm
works, this is necessarily the shortest possible match at the first possible
matching point in the subject string.
.sp
  PCRE2_DFA_RESTART
.sp
When \fBpcre2_dfa_match()\fP 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
\fIworkspace\fP and \fIwscount\fP 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
.\" HREF
\fBpcre2partial\fP
.\"
documentation.
.
.
.SS "Successful returns from \fBpcre2_dfa_match()\fP"
.rs
.sp
When \fBpcre2_dfa_match()\fP succeeds, it may have matched more than one
substring 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, if the pattern
.sp
  <.*>
.sp
is matched against the string
.sp
  This is <something> <something else> <something further> no more
.sp
the three matched strings are
.sp
  <something>
  <something> <something else>
  <something> <something else> <something further>
.sp
On success, the yield of the function is a number greater than zero, which is
the number of matched substrings. The offsets of the substrings are returned in
the ovector, and can be extracted in the same way as for \fBpcre2_match()\fP.
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 function is zero, and the vector is filled with
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.
.
.
.SS "Error returns from \fBpcre2_dfa_match()\fP"
.rs
.sp
The \fBpcre2_dfa_match()\fP function returns a negative number when it fails.
Many of the errors are the same as for \fBpcre2_match()\fP, as described
.\" HTML <a href="#errorlist">
.\" </a>
above.
.\"
There are in addition the following errors that are specific to
\fBpcre2_dfa_match()\fP:
.sp
  PCRE2_ERROR_DFA_UITEM
.sp
This return is given if \fBpcre2_dfa_match()\fP encounters an item in the
pattern that it does not support, for instance, the use of \eC or a back
reference.
.sp
  PCRE2_ERROR_DFA_UCOND
.sp
This return is given if \fBpcre2_dfa_match()\fP encounters a condition item
that uses a back reference for the condition, or a test for recursion in a
specific group. These are not supported.
.sp
  PCRE2_ERROR_DFA_WSSIZE
.sp
This return is given if \fBpcre2_dfa_match()\fP runs out of space in the
\fIworkspace\fP vector.
.sp
  PCRE2_ERROR_DFA_RECURSE
.sp
When a recursive subpattern is processed, the matching function calls itself
recursively, using private memory for the ovector and \fIworkspace\fP. This
error is given if the internal ovector is not large enough. This should be
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,
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.
.
.
.SH "SEE ALSO"
.rs
.sp
\fBpcre2build\fP(3), \fBpcre2libs\fP(3), \fBpcre2callout\fP(3), 
\fBpcre2matching\fP(3), \fBpcre2partial\fP(3), \fBpcre2posix\fP(3), 
\fBpcre2demo(3)\fP, \fBpcre2sample\fP(3), \fBpcre2stack\fP(3).
.
.
.SH AUTHOR
.rs
.sp
.nf
Philip Hazel
University Computing Service
Cambridge CB2 3QH, England.
.fi
.
.
.SH REVISION
.rs
.sp
.nf
Last updated: 05 October 2014
Copyright (c) 1997-2014 University of Cambridge.
.fi