doc: formatting/typo fixes to documentation (#47)

* doc: fix incorrect use of JOIN and typo

Signed-off-by: Carlo Marcelo Arenas Belón <carenas@gmail.com>

* doc: reformat of pcre2_substitute to align options

includes some rewording to fit better in an 80 char wide troff output.

Signed-off-by: Carlo Marcelo Arenas Belón <carenas@gmail.com>

* doc: update names to pcre2

doc/html/pcre2_set_compile_extra_options.html

@@ -30,8 +30,8 @@ This function sets additional option bits for <b>pcre2_compile()</b> that are
 housed in a compile context. It completely replaces all the bits. The extra
 options are:
 <pre>
-  PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK     Allow \K in lookarounds PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES  Allow \x{df800} to \x{dfff}
+  PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK     Allow \K in lookarounds
-                                         in UTF-8 and UTF-32 modes
+  PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES  Allow \x{d800} to \x{dfff} in UTF-8 and UTF-32 modes
   PCRE2_EXTRA_ALT_BSUX                 Extended alternate \u, \U, and \x handling
   PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL    Treat all invalid escapes as a literal following character
   PCRE2_EXTRA_ESCAPED_CR_IS_LF         Interpret \r as \n

doc/html/pcre2_substitute.html

@@ -69,18 +69,18 @@ The subject and replacement lengths can be given as PCRE2_ZERO_TERMINATED for
 zero-terminated strings. The options are:
 <pre>
   PCRE2_ANCHORED                     Match only at the first position
-  PCRE2_ENDANCHORED          Pattern can match only at end of subject
+  PCRE2_ENDANCHORED                  Match only at end of subject
   PCRE2_NOTBOL                       Subject is not the beginning of a line
   PCRE2_NOTEOL                       Subject is not the end of a line
   PCRE2_NOTEMPTY                     An empty string is not a valid match
   PCRE2_NOTEMPTY_ATSTART             An empty string at the start of the subject is not a valid match
   PCRE2_NO_JIT                       Do not use JIT matching
-  PCRE2_NO_UTF_CHECK         Do not check the subject or replacement for UTF validity (only relevant if
+  PCRE2_NO_UTF_CHECK                 Do not check for UTF validity in the subject or replacement
-                              PCRE2_UTF was set at compile time)
+                                      (only relevant if PCRE2_UTF was set at compile time)
   PCRE2_SUBSTITUTE_EXTENDED          Do extended replacement processing
   PCRE2_SUBSTITUTE_GLOBAL            Replace all occurrences in the subject
   PCRE2_SUBSTITUTE_LITERAL           The replacement string is literal
-  PCRE2_SUBSTITUTE_MATCHED   Use pre-existing match data for 1st match
+  PCRE2_SUBSTITUTE_MATCHED           Use pre-existing match data for first match
   PCRE2_SUBSTITUTE_OVERFLOW_LENGTH   If overflow, compute needed length
   PCRE2_SUBSTITUTE_REPLACEMENT_ONLY  Return only replacement string(s)
   PCRE2_SUBSTITUTE_UNKNOWN_UNSET     Treat unknown group as unset
@@ -90,7 +90,7 @@ If PCRE2_SUBSTITUTE_LITERAL is set, PCRE2_SUBSTITUTE_EXTENDED,
 PCRE2_SUBSTITUTE_UNKNOWN_UNSET, and PCRE2_SUBSTITUTE_UNSET_EMPTY are ignored.
 </P>
 <P>
-If PCRE2_SUBSTITUTE_MATCHED is set, <i>match_data</i> must be non-zero; its
+If PCRE2_SUBSTITUTE_MATCHED is set, <i>match_data</i> must be non-NULL; its
 contents must be the result of a call to <b>pcre2_match()</b> using the same
 pattern and subject.
 </P>

doc/html/pcre2pattern.html

@@ -534,7 +534,7 @@ for themselves. For example, outside a character class:
   \0113  is a tab followed by the character "3"
   \113   might be a backreference, otherwise the character with octal code 113
   \377   might be a backreference, otherwise the value 255 (decimal)
-  \81    is always a backreference .sp
+  \81    is always a backreference
 </pre>
 Note that octal values of 100 or greater that are specified using this syntax
 must not be introduced by a leading zero, because no more than three octal

doc/pcre2_set_compile_extra_options.3

@@ -18,9 +18,9 @@ This function sets additional option bits for \fBpcre2_compile()\fP that are
 housed in a compile context. It completely replaces all the bits. The extra
 options are:
 .sp
-.\" JOIN
   PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK     Allow \eK in lookarounds
-  PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES  Allow \ex{df800} to \ex{dfff}
+.\" JOIN
+  PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES  Allow \ex{d800} to \ex{dfff}
                                          in UTF-8 and UTF-32 modes
 .\" JOIN
   PCRE2_EXTRA_ALT_BSUX                 Extended alternate \eu, \eU, and

doc/pcre2_substitute.3

@@ -56,22 +56,32 @@ The subject and replacement lengths can be given as PCRE2_ZERO_TERMINATED for
 zero-terminated strings. The options are:
 .sp
   PCRE2_ANCHORED                     Match only at the first position
-  PCRE2_ENDANCHORED          Pattern can match only at end of subject
+  PCRE2_ENDANCHORED                  Match only at end of subject
-  PCRE2_NOTBOL               Subject is not the beginning of a line
-  PCRE2_NOTEOL               Subject is not the end of a line
-  PCRE2_NOTEMPTY             An empty string is not a valid match
 .\" JOIN
-  PCRE2_NOTEMPTY_ATSTART     An empty string at the start of the
+  PCRE2_NOTBOL                       Subject is not the beginning of a
-                              subject is not a valid match
+                                      line
+  PCRE2_NOTEOL                       Subject is not the end of a line
+.\" JOIN
+  PCRE2_NOTEMPTY                     An empty string is not a
+                                      valid match
+.\" JOIN
+  PCRE2_NOTEMPTY_ATSTART             An empty string at the start of
+                                      the subject is not a valid match
   PCRE2_NO_JIT                       Do not use JIT matching
 .\" JOIN
-  PCRE2_NO_UTF_CHECK         Do not check the subject or replacement
+  PCRE2_NO_UTF_CHECK                 Do not check for UTF validity in
-                              for UTF validity (only relevant if
+                                      the subject or replacement
-                              PCRE2_UTF was set at compile time)
+.\" JOIN
+                                      (only relevant if PCRE2_UTF was
+                                      set at compile time)
   PCRE2_SUBSTITUTE_EXTENDED          Do extended replacement processing
-  PCRE2_SUBSTITUTE_GLOBAL    Replace all occurrences in the subject
+.\" JOIN
+  PCRE2_SUBSTITUTE_GLOBAL            Replace all occurrences in the
+                                      subject
   PCRE2_SUBSTITUTE_LITERAL           The replacement string is literal
-  PCRE2_SUBSTITUTE_MATCHED   Use pre-existing match data for 1st match
+.\" JOIN
+  PCRE2_SUBSTITUTE_MATCHED           Use pre-existing match data for
+                                      first match
   PCRE2_SUBSTITUTE_OVERFLOW_LENGTH   If overflow, compute needed length
   PCRE2_SUBSTITUTE_REPLACEMENT_ONLY  Return only replacement string(s)
   PCRE2_SUBSTITUTE_UNKNOWN_UNSET     Treat unknown group as unset
@@ -80,7 +90,7 @@ zero-terminated strings. The options are:
 If PCRE2_SUBSTITUTE_LITERAL is set, PCRE2_SUBSTITUTE_EXTENDED,
 PCRE2_SUBSTITUTE_UNKNOWN_UNSET, and PCRE2_SUBSTITUTE_UNSET_EMPTY are ignored.
 .P
-If PCRE2_SUBSTITUTE_MATCHED is set, \fImatch_data\fP must be non-zero; its
+If PCRE2_SUBSTITUTE_MATCHED is set, \fImatch_data\fP must be non-NULL; its
 contents must be the result of a call to \fBpcre2_match()\fP using the same
 pattern and subject.
 .P

doc/pcre2api.3

@@ -1794,7 +1794,7 @@ 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.
 .P
 Note that this option can also be passed to \fBpcre2_match()\fP and
-\fBpcre_dfa_match()\fP, to suppress UTF validity checking of the subject
+\fBpcre2_dfa_match()\fP, to suppress UTF validity checking of the subject
 string.
 .P
 Note also that setting PCRE2_NO_UTF_CHECK at compile time does not disable the
@@ -3848,7 +3848,7 @@ Here is an example of a simple call to \fBpcre2_dfa_match()\fP:
     wspace,         /* working space vector */
     20);            /* number of elements (NOT size in bytes) */
 .
-.SS "Option bits for \fBpcre_dfa_match()\fP"
+.SS "Option bits for \fBpcre2_dfa_match()\fP"
 .rs
 .sp
 The unused bits of the \fIoptions\fP argument for \fBpcre2_dfa_match()\fP must

doc/pcre2pattern.3

@@ -509,7 +509,6 @@ for themselves. For example, outside a character class:
 .\" JOIN
   \e377   might be a backreference, otherwise
             the value 255 (decimal)
-.\" JOIN
   \e81    is always a backreference
 .sp
 Note that octal values of 100 or greater that are specified using this syntax

doc/pcre2test.1

@@ -47,7 +47,7 @@ format before being passed to the library functions. Results are converted back
 to 8-bit code units for output.
 .P
 In the rest of this document, the names of library functions and structures
-are given in generic form, for example, \fBpcre_compile()\fP. The actual
+are given in generic form, for example, \fBpcre2_compile()\fP. The actual
 names used in the libraries have a suffix _8, _16, or _32, as appropriate.
 .
 .

src/pcre2_intmodedep.h

@@ -519,7 +519,7 @@ it is. This is called only in UTF-32 mode - we don't put a test within the
 macro because almost all calls are already within a block of UTF-32 only
 code.
 
-These are all no-ops since all UTF-32 characters fit into one pcre_uchar. */
+These are all no-ops since all UTF-32 characters fit into one PCRE2_UCHAR. */
 
 #define BACKCHAR(eptr) do { } while (0)
 
@@ -764,7 +764,7 @@ typedef struct pcre2_real_jit_stack {
 } pcre2_real_jit_stack;
 
 /* Structure for items in a linked list that represents an explicit recursive
-call within the pattern when running pcre_dfa_match(). */
+call within the pattern when running pcre2_dfa_match(). */
 
 typedef struct dfa_recursion_info {
   struct dfa_recursion_info *prevrec;

src/pcre2_jit_compile.c

@@ -13692,7 +13692,7 @@ if (!compiler)
   }
 common->compiler = compiler;
 
-/* Main pcre_jit_exec entry. */
+/* Main pcre2_jit_exec entry. */
 sljit_emit_enter(compiler, 0, SLJIT_ARG1(SW), 5, 5, 0, 0, private_data_size);
 
 /* Register init. */

src/pcre2_jit_match.c

@@ -120,7 +120,7 @@ else if ((options & PCRE2_PARTIAL_SOFT) != 0)
 if (functions == NULL || functions->executable_funcs[index] == NULL)
   return PCRE2_ERROR_JIT_BADOPTION;
 
-/* Sanity checks should be handled by pcre_exec. */
+/* Sanity checks should be handled by pcre2_match. */
 arguments.str = subject + start_offset;
 arguments.begin = subject;
 arguments.end = subject + length;

src/pcre2_jit_test.c

@@ -108,7 +108,7 @@ int main(void)
 	pcre2_config_32(PCRE2_CONFIG_JIT, &jit);
 #endif
 	if (!jit) {
-		printf("JIT must be enabled to run pcre_jit_test\n");
+		printf("JIT must be enabled to run pcre2_jit_test\n");
 		return 1;
 	}
 	return regression_tests()
@@ -1200,8 +1200,8 @@ static int regression_tests(void)
 #endif
 
 	/* This test compares the behaviour of interpreter and JIT. Although disabling
-	utf or ucp may make tests fail, if the pcre_exec result is the SAME, it is
+	utf or ucp may make tests fail, if the pcre2_match result is the SAME, it is
-	still considered successful from pcre_jit_test point of view. */
+	still considered successful from pcre2_jit_test point of view. */
 
 #if defined SUPPORT_PCRE2_8
 	pcre2_config_8(PCRE2_CONFIG_JITTARGET, &cpu_info);

src/pcre2grep.c

@@ -1816,7 +1816,7 @@ to find all possible matches.
 Arguments:
   matchptr     the start of the subject
   length       the length of the subject to match
-  options      options for pcre_exec
+  options      options for pcre2_match
   startoffset  where to start matching
   mrc          address of where to put the result of pcre2_match()
 

testdata/testinput7

@@ -1,5 +1,5 @@
 # This set of tests checks UTF and Unicode property support with the DFA
-# matching functionality of pcre_dfa_match(). A default subject modifier is
+# matching functionality of pcre2_dfa_match(). A default subject modifier is
 # used to force DFA matching for all tests.
 
 #subject dfa

testdata/testoutput7

@@ -1,5 +1,5 @@
 # This set of tests checks UTF and Unicode property support with the DFA
-# matching functionality of pcre_dfa_match(). A default subject modifier is
+# matching functionality of pcre2_dfa_match(). A default subject modifier is
 # used to force DFA matching for all tests.
 
 #subject dfa