| .TH PCREAPI 3 |
| .SH NAME |
| PCRE - Perl-compatible regular expressions |
| .SH "PCRE NATIVE API BASIC FUNCTIONS" |
| .rs |
| .sp |
| .B #include <pcre.h> |
| .PP |
| .SM |
| .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, |
| .ti +5n |
| .B const char **\fIerrptr\fP, int *\fIerroffset\fP, |
| .ti +5n |
| .B const unsigned char *\fItableptr\fP); |
| .PP |
| .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, |
| .ti +5n |
| .B int *\fIerrorcodeptr\fP, |
| .ti +5n |
| .B const char **\fIerrptr\fP, int *\fIerroffset\fP, |
| .ti +5n |
| .B const unsigned char *\fItableptr\fP); |
| .PP |
| .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, |
| .ti +5n |
| .B const char **\fIerrptr\fP); |
| .PP |
| .B void pcre_free_study(pcre_extra *\fIextra\fP); |
| .PP |
| .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," |
| .ti +5n |
| .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, |
| .ti +5n |
| .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); |
| . |
| . |
| .SH "PCRE NATIVE API AUXILIARY FUNCTIONS" |
| .rs |
| .sp |
| .B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP); |
| .PP |
| .B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP); |
| .PP |
| .B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP, |
| .ti +5n |
| .B pcre_jit_callback \fIcallback\fP, void *\fIdata\fP); |
| .PP |
| .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," |
| .ti +5n |
| .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, |
| .ti +5n |
| .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, |
| .ti +5n |
| .B int *\fIworkspace\fP, int \fIwscount\fP); |
| .PP |
| .B int pcre_copy_named_substring(const pcre *\fIcode\fP, |
| .ti +5n |
| .B const char *\fIsubject\fP, int *\fIovector\fP, |
| .ti +5n |
| .B int \fIstringcount\fP, const char *\fIstringname\fP, |
| .ti +5n |
| .B char *\fIbuffer\fP, int \fIbuffersize\fP); |
| .PP |
| .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, |
| .ti +5n |
| .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, |
| .ti +5n |
| .B int \fIbuffersize\fP); |
| .PP |
| .B int pcre_get_named_substring(const pcre *\fIcode\fP, |
| .ti +5n |
| .B const char *\fIsubject\fP, int *\fIovector\fP, |
| .ti +5n |
| .B int \fIstringcount\fP, const char *\fIstringname\fP, |
| .ti +5n |
| .B const char **\fIstringptr\fP); |
| .PP |
| .B int pcre_get_stringnumber(const pcre *\fIcode\fP, |
| .ti +5n |
| .B const char *\fIname\fP); |
| .PP |
| .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, |
| .ti +5n |
| .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); |
| .PP |
| .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, |
| .ti +5n |
| .B int \fIstringcount\fP, int \fIstringnumber\fP, |
| .ti +5n |
| .B const char **\fIstringptr\fP); |
| .PP |
| .B int pcre_get_substring_list(const char *\fIsubject\fP, |
| .ti +5n |
| .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" |
| .PP |
| .B void pcre_free_substring(const char *\fIstringptr\fP); |
| .PP |
| .B void pcre_free_substring_list(const char **\fIstringptr\fP); |
| .PP |
| .B const unsigned char *pcre_maketables(void); |
| .PP |
| .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," |
| .ti +5n |
| .B int \fIwhat\fP, void *\fIwhere\fP); |
| .PP |
| .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int |
| .B *\fIfirstcharptr\fP); |
| .PP |
| .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); |
| .PP |
| .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); |
| .PP |
| .B char *pcre_version(void); |
| . |
| . |
| .SH "PCRE NATIVE API INDIRECTED FUNCTIONS" |
| .rs |
| .sp |
| .B void *(*pcre_malloc)(size_t); |
| .PP |
| .B void (*pcre_free)(void *); |
| .PP |
| .B void *(*pcre_stack_malloc)(size_t); |
| .PP |
| .B void (*pcre_stack_free)(void *); |
| .PP |
| .B int (*pcre_callout)(pcre_callout_block *); |
| . |
| . |
| .SH "PCRE API OVERVIEW" |
| .rs |
| .sp |
| PCRE has its own native API, which is described in this document. There are |
| also some wrapper functions that correspond to the POSIX regular expression |
| API, but they do not give access to all the functionality. They are described |
| in the |
| .\" HREF |
| \fBpcreposix\fP |
| .\" |
| documentation. Both of these APIs define a set of C function calls. A C++ |
| wrapper is also distributed with PCRE. It is documented in the |
| .\" HREF |
| \fBpcrecpp\fP |
| .\" |
| page. |
| .P |
| The native API C function prototypes are defined in the header file |
| \fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP. |
| It can normally be accessed by adding \fB-lpcre\fP to the command for linking |
| an application that uses PCRE. The header file defines the macros PCRE_MAJOR |
| and PCRE_MINOR to contain the major and minor release numbers for the library. |
| Applications can use these to include support for different releases of PCRE. |
| .P |
| In a Windows environment, if you want to statically link an application program |
| against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before |
| including \fBpcre.h\fP or \fBpcrecpp.h\fP, because otherwise the |
| \fBpcre_malloc()\fP and \fBpcre_free()\fP exported functions will be declared |
| \fB__declspec(dllimport)\fP, with unwanted results. |
| .P |
| The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP, |
| and \fBpcre_exec()\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 \fIpcredemo.c\fP in the PCRE |
| source distribution. A listing of this program is given in the |
| .\" HREF |
| \fBpcredemo\fP |
| .\" |
| documentation, and the |
| .\" HREF |
| \fBpcresample\fP |
| .\" |
| documentation describes how to compile and run it. |
| .P |
| Just-in-time compiler support is an optional feature of PCRE that can be built |
| in appropriate hardware environments. It greatly speeds up the matching |
| performance of many patterns. Simple programs can easily request that it be |
| used if available, by setting an option that is ignored when it is not |
| relevant. More complicated programs might need to make use of the functions |
| \fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and |
| \fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage. |
| These functions are discussed in the |
| .\" HREF |
| \fBpcrejit\fP |
| .\" |
| documentation. |
| .P |
| A second matching function, \fBpcre_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 |
| \fBpcrematching\fP |
| .\" |
| documentation. |
| .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 \fBpcre_exec()\fP. They are: |
| .sp |
| \fBpcre_copy_substring()\fP |
| \fBpcre_copy_named_substring()\fP |
| \fBpcre_get_substring()\fP |
| \fBpcre_get_named_substring()\fP |
| \fBpcre_get_substring_list()\fP |
| \fBpcre_get_stringnumber()\fP |
| \fBpcre_get_stringtable_entries()\fP |
| .sp |
| \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also |
| provided, to free the memory used for extracted strings. |
| .P |
| The function \fBpcre_maketables()\fP is used to build a set of character tables |
| in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP, |
| or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for |
| specialist use. Most commonly, no special tables are passed, in which case |
| internal tables that are generated when PCRE is built are used. |
| .P |
| The function \fBpcre_fullinfo()\fP is used to find out information about a |
| compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only |
| some of the available information, but is retained for backwards compatibility. |
| The function \fBpcre_version()\fP returns a pointer to a string containing the |
| version of PCRE and its date of release. |
| .P |
| The function \fBpcre_refcount()\fP maintains a reference count in a data block |
| containing a compiled pattern. This is provided for the benefit of |
| object-oriented applications. |
| .P |
| The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain |
| the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions, |
| respectively. PCRE calls the memory management functions via these variables, |
| so a calling program can replace them if it wishes to intercept the calls. This |
| should be done before calling any PCRE functions. |
| .P |
| The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also |
| indirections to memory management functions. These special functions are used |
| only when PCRE is compiled to use the heap for remembering data, instead of |
| recursive function calls, when running the \fBpcre_exec()\fP function. See the |
| .\" HREF |
| \fBpcrebuild\fP |
| .\" |
| documentation for details of how to do this. It is a non-standard way of |
| building PCRE, for use in environments that have limited stacks. Because of the |
| greater use of memory management, it runs more slowly. Separate functions are |
| provided so that special-purpose external code can be used for this case. When |
| used, these functions are always called in a stack-like manner (last obtained, |
| first freed), and always for memory blocks of the same size. There is a |
| discussion about PCRE's stack usage in the |
| .\" HREF |
| \fBpcrestack\fP |
| .\" |
| documentation. |
| .P |
| The global variable \fBpcre_callout\fP initially contains NULL. It can be set |
| by the caller to a "callout" function, which PCRE will then call at specified |
| points during a matching operation. Details are given in the |
| .\" HREF |
| \fBpcrecallout\fP |
| .\" |
| documentation. |
| . |
| . |
| .\" HTML <a name="newlines"></a> |
| .SH NEWLINES |
| .rs |
| .sp |
| PCRE 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 (formfeed, |
| 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 PCRE is built, a default can be specified. |
| The default default is LF, which is the Unix standard. When PCRE is run, the |
| default can be overridden, either when a pattern is compiled, or when it is |
| matched. |
| .P |
| At compile time, the newline convention can be specified by the \fIoptions\fP |
| argument of \fBpcre_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 |
| \fBpcrepattern\fP |
| .\" |
| page for details of the special character sequences. |
| .P |
| In the PCRE 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="#execoptions"> |
| .\" </a> |
| section on \fBpcre_exec()\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 is |
| controlled in a similar way, but by separate options. |
| . |
| . |
| .SH MULTITHREADING |
| .rs |
| .sp |
| The PCRE functions can be used in multi-threading applications, with the |
| proviso that the memory management functions pointed to by \fBpcre_malloc\fP, |
| \fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the |
| callout function pointed to by \fBpcre_callout\fP, are shared by all threads. |
| .P |
| The compiled form of a regular expression is not altered during matching, so |
| the same compiled pattern can safely be used by several threads at once. |
| .P |
| If the just-in-time optimization feature is being used, it needs separate |
| memory stack areas for each thread. See the |
| .\" HREF |
| \fBpcrejit\fP |
| .\" |
| documentation for more details. |
| . |
| . |
| .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE" |
| .rs |
| .sp |
| The compiled form of a regular expression can be saved and re-used at a later |
| time, possibly by a different program, and even on a host other than the one on |
| which it was compiled. Details are given in the |
| .\" HREF |
| \fBpcreprecompile\fP |
| .\" |
| documentation. However, compiling a regular expression with one version of PCRE |
| for use with a different version is not guaranteed to work and may cause |
| crashes. |
| . |
| . |
| .SH "CHECKING BUILD-TIME OPTIONS" |
| .rs |
| .sp |
| .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); |
| .PP |
| The function \fBpcre_config()\fP makes it possible for a PCRE client to |
| discover which optional features have been compiled into the PCRE library. The |
| .\" HREF |
| \fBpcrebuild\fP |
| .\" |
| documentation has more details about these optional features. |
| .P |
| The first argument for \fBpcre_config()\fP is an integer, specifying which |
| information is required; the second argument is a pointer to a variable into |
| which the information is placed. The following information is available: |
| .sp |
| PCRE_CONFIG_UTF8 |
| .sp |
| The output is an integer that is set to one if UTF-8 support is available; |
| otherwise it is set to zero. |
| .sp |
| PCRE_CONFIG_UNICODE_PROPERTIES |
| .sp |
| The output is an integer that is set to one if support for Unicode character |
| properties is available; otherwise it is set to zero. |
| .sp |
| PCRE_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 |
| PCRE_CONFIG_NEWLINE |
| .sp |
| The output is an integer whose value specifies the default character sequence |
| that is recognized as meaning "newline". The four values that are supported |
| are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. |
| Though they are derived from ASCII, the same values are returned in EBCDIC |
| environments. The default should normally correspond to the standard sequence |
| for your operating system. |
| .sp |
| PCRE_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 |
| PCRE_CONFIG_LINK_SIZE |
| .sp |
| The output is an integer that contains the number of bytes used for internal |
| linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values |
| allow larger regular expressions to be compiled, at the expense of slower |
| matching. The default value of 2 is sufficient for all but the most massive |
| patterns, since it allows the compiled pattern to be up to 64K in size. |
| .sp |
| PCRE_CONFIG_POSIX_MALLOC_THRESHOLD |
| .sp |
| The output is an integer that contains the threshold above which the POSIX |
| interface uses \fBmalloc()\fP for output vectors. Further details are given in |
| the |
| .\" HREF |
| \fBpcreposix\fP |
| .\" |
| documentation. |
| .sp |
| PCRE_CONFIG_MATCH_LIMIT |
| .sp |
| The output is a long integer that gives the default limit for the number of |
| internal matching function calls in a \fBpcre_exec()\fP execution. Further |
| details are given with \fBpcre_exec()\fP below. |
| .sp |
| PCRE_CONFIG_MATCH_LIMIT_RECURSION |
| .sp |
| The output is a long integer that gives the default limit for the depth of |
| recursion when calling the internal matching function in a \fBpcre_exec()\fP |
| execution. Further details are given with \fBpcre_exec()\fP below. |
| .sp |
| PCRE_CONFIG_STACKRECURSE |
| .sp |
| The output is an integer that is set to one if internal recursion when running |
| \fBpcre_exec()\fP is implemented by recursive function calls that use the stack |
| to remember their state. This is the usual way that PCRE is compiled. The |
| output is zero if PCRE was compiled to use blocks of data on the heap instead |
| of recursive function calls. In this case, \fBpcre_stack_malloc\fP and |
| \fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus |
| avoiding the use of the stack. |
| . |
| . |
| .SH "COMPILING A PATTERN" |
| .rs |
| .sp |
| .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, |
| .ti +5n |
| .B const char **\fIerrptr\fP, int *\fIerroffset\fP, |
| .ti +5n |
| .B const unsigned char *\fItableptr\fP); |
| .sp |
| .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, |
| .ti +5n |
| .B int *\fIerrorcodeptr\fP, |
| .ti +5n |
| .B const char **\fIerrptr\fP, int *\fIerroffset\fP, |
| .ti +5n |
| .B const unsigned char *\fItableptr\fP); |
| .P |
| Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be |
| called to compile a pattern into an internal form. The only difference between |
| the two interfaces is that \fBpcre_compile2()\fP has an additional argument, |
| \fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid |
| too much repetition, we refer just to \fBpcre_compile()\fP below, but the |
| information applies equally to \fBpcre_compile2()\fP. |
| .P |
| The pattern is a C string terminated by a binary zero, and is passed in the |
| \fIpattern\fP argument. A pointer to a single block of memory that is obtained |
| via \fBpcre_malloc\fP is returned. This contains the compiled code and related |
| data. The \fBpcre\fP type is defined for the returned block; this is a typedef |
| for a structure whose contents are not externally defined. It is up to the |
| caller to free the memory (via \fBpcre_free\fP) when it is no longer required. |
| .P |
| Although the compiled code of a PCRE regex is relocatable, that is, it does not |
| depend on memory location, the complete \fBpcre\fP data block is not |
| fully relocatable, because it may contain a copy of the \fItableptr\fP |
| argument, which is an address (see below). |
| .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 |
| \fBpcrepattern\fP |
| .\" |
| documentation). 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 and execution. The PCRE_ANCHORED, |
| PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and |
| PCRE_NO_START_OPT options can be set at the time of matching as well as at |
| compile time. |
| .P |
| If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately. |
| Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns |
| NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual |
| error message. This is a static string that is part of the library. You must |
| not try to free it. Normally, the offset from the start of the pattern to the |
| byte that was being processed when the error was discovered is placed in the |
| variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an |
| immediate error is given). However, for an invalid UTF-8 string, the offset is |
| that of the first byte of the failing character. Also, some errors are not |
| detected until checks are carried out when the whole pattern has been scanned; |
| in these cases the offset passed back is the length of the pattern. |
| .P |
| Note that the offset is in bytes, not characters, even in UTF-8 mode. It may |
| sometimes point into the middle of a UTF-8 character. |
| .P |
| If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the |
| \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is |
| returned via this argument in the event of an error. This is in addition to the |
| textual error message. Error codes and messages are listed below. |
| .P |
| If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of |
| character tables that are built when PCRE is compiled, using the default C |
| locale. Otherwise, \fItableptr\fP must be an address that is the result of a |
| call to \fBpcre_maketables()\fP. This value is stored with the compiled |
| pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is |
| passed to it. For more discussion, see the section on locale support below. |
| .P |
| This code fragment shows a typical straightforward call to \fBpcre_compile()\fP: |
| .sp |
| pcre *re; |
| const char *error; |
| int erroffset; |
| re = pcre_compile( |
| "^A.*Z", /* the pattern */ |
| 0, /* default options */ |
| &error, /* for error message */ |
| &erroffset, /* for error offset */ |
| NULL); /* use default character tables */ |
| .sp |
| The following names for option bits are defined in the \fBpcre.h\fP header |
| file: |
| .sp |
| PCRE_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 |
| PCRE_AUTO_CALLOUT |
| .sp |
| If this bit is set, \fBpcre_compile()\fP automatically inserts callout items, |
| all with number 255, before each pattern item. For discussion of the callout |
| facility, see the |
| .\" HREF |
| \fBpcrecallout\fP |
| .\" |
| documentation. |
| .sp |
| PCRE_BSR_ANYCRLF |
| PCRE_BSR_UNICODE |
| .sp |
| These options (which are mutually exclusive) control what the \eR escape |
| sequence matches. The choice is either to match only CR, LF, or CRLF, or to |
| match any Unicode newline sequence. The default is specified when PCRE is |
| built. It can be overridden from within the pattern, or by setting an option |
| when a compiled pattern is matched. |
| .sp |
| PCRE_CASELESS |
| .sp |
| If this bit is set, letters in the pattern match both upper and lower case |
| letters. It is equivalent to Perl's /i option, and it can be changed within a |
| pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the |
| concept of case for characters whose values are less than 128, so caseless |
| matching is always possible. For characters with higher values, the concept of |
| case is supported if PCRE is compiled with Unicode property support, but not |
| otherwise. If you want to use caseless matching for characters 128 and above, |
| you must ensure that PCRE is compiled with Unicode property support as well as |
| with UTF-8 support. |
| .sp |
| PCRE_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 PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. |
| There is no equivalent to this option in Perl, and no way to set it within a |
| pattern. |
| .sp |
| PCRE_DOTALL |
| .sp |
| If this bit is set, a dot metacharacter in the pattern matches a character of |
| any value, 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 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 |
| PCRE_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 |
| \fBpcrepattern\fP |
| .\" |
| documentation. |
| .sp |
| PCRE_EXTENDED |
| .sp |
| If this bit is set, whitespace data characters in the pattern are totally |
| ignored except when escaped or inside a character class. Whitespace does not |
| include the VT character (code 11). In addition, characters between an |
| unescaped # outside a character class and the next newline, inclusive, are also |
| ignored. This 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 is controlled by the options |
| passed to \fBpcre_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 \fBpcrepattern\fP documentation. 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. |
| .P |
| This option makes it possible to include comments inside complicated patterns. |
| Note, however, that this applies only to data characters. Whitespace characters |
| may never appear within special character sequences in a pattern, for example |
| within the sequence (?( that introduces a conditional subpattern. |
| .sp |
| PCRE_EXTRA |
| .sp |
| This option was invented in order to turn on additional functionality of PCRE |
| that is incompatible with Perl, but it is currently of very little use. When |
| set, any backslash in a pattern that is followed by a letter that has no |
| special meaning causes an error, thus reserving these combinations for future |
| expansion. By default, as in Perl, a backslash followed by a letter with no |
| special meaning is treated as a literal. (Perl can, however, be persuaded to |
| give an error for this, by running it with the -w option.) There are at present |
| no other features controlled by this option. It can also be set by a (?X) |
| option setting within a pattern. |
| .sp |
| PCRE_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 |
| PCRE_JAVASCRIPT_COMPAT |
| .sp |
| If this option is set, PCRE's behaviour is changed in some ways so that it is |
| compatible with JavaScript rather than Perl. The changes are as follows: |
| .P |
| (1) A lone closing square bracket in a pattern causes a compile-time error, |
| because this is illegal in JavaScript (by default it is treated as a data |
| character). Thus, the pattern AB]CD becomes illegal when this option is set. |
| .P |
| (2) At run time, 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. |
| .P |
| (3) \eU matches an upper case "U" character; by default \eU causes a compile |
| time error (Perl uses \eU to upper case subsequent characters). |
| .P |
| (4) \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 |
| (5) \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 |
| PCRE_MULTILINE |
| .sp |
| By default, PCRE 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, while the "end of |
| line" metacharacter ($) matches only at the end of the string, or before a |
| terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as |
| Perl. |
| .P |
| When PCRE_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 PCRE_MULTILINE has no effect. |
| .sp |
| PCRE_NEWLINE_CR |
| PCRE_NEWLINE_LF |
| PCRE_NEWLINE_CRLF |
| PCRE_NEWLINE_ANYCRLF |
| PCRE_NEWLINE_ANY |
| .sp |
| These options override the default newline definition that was chosen when PCRE |
| was built. Setting the first or the second specifies that a newline is |
| indicated by a single character (CR or LF, respectively). Setting |
| PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character |
| CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three |
| preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies |
| that any Unicode newline sequence should be recognized. The Unicode newline |
| sequences are the three just mentioned, plus the single characters VT (vertical |
| tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line |
| separator, U+2028), and PS (paragraph separator, U+2029). The last two are |
| recognized only in UTF-8 mode. |
| .P |
| The newline setting in the options word uses three bits that are treated |
| as a number, giving eight possibilities. Currently only six are used (default |
| plus the five values above). This means that if you set more than one newline |
| option, the combination may or may not be sensible. For example, |
| PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but |
| other combinations may yield unused numbers and cause an error. |
| .P |
| The only time that a line break in a pattern is specially recognized when |
| compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters, |
| and so are ignored in this mode. Also, an unescaped # outside a character class |
| indicates a comment that lasts until after the next line break sequence. In |
| other circumstances, line break sequences in patterns are treated as literal |
| data. |
| .P |
| The newline option that is set at compile time becomes the default that is used |
| for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden. |
| .sp |
| PCRE_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 |
| NO_START_OPTIMIZE |
| .sp |
| This is an option that acts at matching time; that is, it is really an option |
| for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time, |
| it is remembered with the compiled pattern and assumed at matching time. For |
| details see the discussion of PCRE_NO_START_OPTIMIZE |
| .\" HTML <a href="#execoptions"> |
| .\" </a> |
| below. |
| .\" |
| .sp |
| PCRE_UCP |
| .sp |
| This option changes the way PCRE 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 PCRE_UCP is set, Unicode properties are used instead to |
| classify characters. More details are given in the section on |
| .\" HTML <a href="pcre.html#genericchartypes"> |
| .\" </a> |
| generic character types |
| .\" |
| in the |
| .\" HREF |
| \fBpcrepattern\fP |
| .\" |
| page. If you set PCRE_UCP, matching one of the items it affects takes much |
| longer. The option is available only if PCRE has been compiled with Unicode |
| property support. |
| .sp |
| PCRE_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 |
| PCRE_UTF8 |
| .sp |
| This option causes PCRE to regard both the pattern and the subject as strings |
| of UTF-8 characters instead of single-byte character strings. However, it is |
| available only when PCRE is built to include UTF-8 support. If not, the use |
| of this option provokes an error. Details of how this option changes the |
| behaviour of PCRE are given in the |
| .\" HREF |
| \fBpcreunicode\fP |
| .\" |
| page. |
| .sp |
| PCRE_NO_UTF8_CHECK |
| .sp |
| When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is |
| automatically checked. There is a discussion about the |
| .\" HTML <a href="pcre.html#utf8strings"> |
| .\" </a> |
| validity of UTF-8 strings |
| .\" |
| in the main |
| .\" HREF |
| \fBpcre\fP |
| .\" |
| page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP |
| returns an error. If you already know that your pattern is valid, and you want |
| to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK |
| option. When it is set, the effect of passing an invalid UTF-8 string as a |
| pattern is undefined. It may cause your program to crash. Note that this option |
| can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress |
| the UTF-8 validity checking of subject strings. |
| . |
| . |
| .SH "COMPILATION ERROR CODES" |
| .rs |
| .sp |
| The following table lists the error codes than may be returned by |
| \fBpcre_compile2()\fP, along with the error messages that may be returned by |
| both compiling functions. As PCRE has developed, some error codes have fallen |
| out of use. To avoid confusion, they have not been re-used. |
| .sp |
| 0 no error |
| 1 \e at end of pattern |
| 2 \ec at end of pattern |
| 3 unrecognized character follows \e |
| 4 numbers out of order in {} quantifier |
| 5 number too big in {} quantifier |
| 6 missing terminating ] for character class |
| 7 invalid escape sequence in character class |
| 8 range out of order in character class |
| 9 nothing to repeat |
| 10 [this code is not in use] |
| 11 internal error: unexpected repeat |
| 12 unrecognized character after (? or (?- |
| 13 POSIX named classes are supported only within a class |
| 14 missing ) |
| 15 reference to non-existent subpattern |
| 16 erroffset passed as NULL |
| 17 unknown option bit(s) set |
| 18 missing ) after comment |
| 19 [this code is not in use] |
| 20 regular expression is too large |
| 21 failed to get memory |
| 22 unmatched parentheses |
| 23 internal error: code overflow |
| 24 unrecognized character after (?< |
| 25 lookbehind assertion is not fixed length |
| 26 malformed number or name after (?( |
| 27 conditional group contains more than two branches |
| 28 assertion expected after (?( |
| 29 (?R or (?[+-]digits must be followed by ) |
| 30 unknown POSIX class name |
| 31 POSIX collating elements are not supported |
| 32 this version of PCRE is not compiled with PCRE_UTF8 support |
| 33 [this code is not in use] |
| 34 character value in \ex{...} sequence is too large |
| 35 invalid condition (?(0) |
| 36 \eC not allowed in lookbehind assertion |
| 37 PCRE does not support \eL, \el, \eN{name}, \eU, or \eu |
| 38 number after (?C is > 255 |
| 39 closing ) for (?C expected |
| 40 recursive call could loop indefinitely |
| 41 unrecognized character after (?P |
| 42 syntax error in subpattern name (missing terminator) |
| 43 two named subpatterns have the same name |
| 44 invalid UTF-8 string |
| 45 support for \eP, \ep, and \eX has not been compiled |
| 46 malformed \eP or \ep sequence |
| 47 unknown property name after \eP or \ep |
| 48 subpattern name is too long (maximum 32 characters) |
| 49 too many named subpatterns (maximum 10000) |
| 50 [this code is not in use] |
| 51 octal value is greater than \e377 (not in UTF-8 mode) |
| 52 internal error: overran compiling workspace |
| 53 internal error: previously-checked referenced subpattern |
| not found |
| 54 DEFINE group contains more than one branch |
| 55 repeating a DEFINE group is not allowed |
| 56 inconsistent NEWLINE options |
| 57 \eg is not followed by a braced, angle-bracketed, or quoted |
| name/number or by a plain number |
| 58 a numbered reference must not be zero |
| 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) |
| 60 (*VERB) not recognized |
| 61 number is too big |
| 62 subpattern name expected |
| 63 digit expected after (?+ |
| 64 ] is an invalid data character in JavaScript compatibility mode |
| 65 different names for subpatterns of the same number are |
| not allowed |
| 66 (*MARK) must have an argument |
| 67 this version of PCRE is not compiled with PCRE_UCP support |
| 68 \ec must be followed by an ASCII character |
| 69 \ek is not followed by a braced, angle-bracketed, or quoted name |
| .sp |
| The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may |
| be used if the limits were changed when PCRE was built. |
| . |
| . |
| .\" HTML <a name="studyingapattern"></a> |
| .SH "STUDYING A PATTERN" |
| .rs |
| .sp |
| .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP |
| .ti +5n |
| .B const char **\fIerrptr\fP); |
| .PP |
| If a compiled pattern is going to be used several times, it is worth spending |
| more time analyzing it in order to speed up the time taken for matching. The |
| function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first |
| argument. If studying the pattern produces additional information that will |
| help speed up matching, \fBpcre_study()\fP returns a pointer to a |
| \fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the |
| results of the study. |
| .P |
| The returned value from \fBpcre_study()\fP can be passed directly to |
| \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. However, a \fBpcre_extra\fP block |
| also contains other fields that can be set by the caller before the block is |
| passed; these are described |
| .\" HTML <a href="#extradata"> |
| .\" </a> |
| below |
| .\" |
| in the section on matching a pattern. |
| .P |
| If studying the pattern does not produce any useful information, |
| \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program |
| wants to pass any of the other fields to \fBpcre_exec()\fP or |
| \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block. |
| .P |
| The second argument of \fBpcre_study()\fP contains option bits. There is only |
| one option: PCRE_STUDY_JIT_COMPILE. If this is set, and the just-in-time |
| compiler is available, the pattern is further compiled into machine code that |
| executes much faster than the \fBpcre_exec()\fP matching function. If |
| the just-in-time compiler is not available, this option is ignored. All other |
| bits in the \fIoptions\fP argument must be zero. |
| .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 study time. |
| Not all patterns can be optimized by the JIT compiler. For those that cannot be |
| handled, matching automatically falls back to the \fBpcre_exec()\fP |
| interpreter. For more details, see the |
| .\" HREF |
| \fBpcrejit\fP |
| .\" |
| documentation. |
| .P |
| The third argument for \fBpcre_study()\fP is a pointer for an error message. If |
| studying succeeds (even if no data is returned), the variable it points to is |
| set to NULL. Otherwise it is set to point to a textual error message. This is a |
| static string that is part of the library. You must not try to free it. You |
| should test the error pointer for NULL after calling \fBpcre_study()\fP, to be |
| sure that it has run successfully. |
| .P |
| When you are finished with a pattern, you can free the memory used for the |
| study data by calling \fBpcre_free_study()\fP. This function was added to the |
| API for release 8.20. For earlier versions, the memory could be freed with |
| \fBpcre_free()\fP, just like the pattern itself. This will still work in cases |
| where PCRE_STUDY_JIT_COMPILE is not used, but it is advisable to change to the |
| new function when convenient. |
| .P |
| This is a typical way in which \fBpcre_study\fP() is used (except that in a |
| real application there should be tests for errors): |
| .sp |
| int rc; |
| pcre *re; |
| pcre_extra *sd; |
| re = pcre_compile("pattern", 0, &error, &erroroffset, NULL); |
| sd = pcre_study( |
| re, /* result of pcre_compile() */ |
| 0, /* no options */ |
| &error); /* set to NULL or points to a message */ |
| rc = pcre_exec( /* see below for details of pcre_exec() options */ |
| re, sd, "subject", 7, 0, 0, ovector, 30); |
| ... |
| pcre_free_study(sd); |
| pcre_free(re); |
| .sp |
| Studying a pattern does two things: first, a lower bound for the length of |
| subject string that is needed to match the pattern is computed. This does not |
| mean that there are any strings of that length that match, but it does |
| guarantee that no shorter strings match. The value is used by |
| \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to |
| match strings that are shorter than the lower bound. You can find out the value |
| in a calling program via the \fBpcre_fullinfo()\fP function. |
| .P |
| Studying a pattern is also useful for non-anchored patterns that do not have a |
| single fixed starting character. A bitmap of possible starting bytes is |
| created. This speeds up finding a position in the subject at which to start |
| matching. |
| .P |
| These two optimizations apply to both \fBpcre_exec()\fP and |
| \fBpcre_dfa_exec()\fP. However, they are not used by \fBpcre_exec()\fP if |
| \fBpcre_study()\fP is called with the PCRE_STUDY_JIT_COMPILE option, and |
| just-in-time compiling is successful. The optimizations can be disabled by |
| setting the PCRE_NO_START_OPTIMIZE option when calling \fBpcre_exec()\fP or |
| \fBpcre_dfa_exec()\fP. You might want to do this if your pattern contains |
| callouts or (*MARK) (which cannot be handled by the JIT compiler), and you want |
| to make use of these facilities in cases where matching fails. See the |
| discussion of PCRE_NO_START_OPTIMIZE |
| .\" HTML <a href="#execoptions"> |
| .\" </a> |
| below. |
| .\" |
| . |
| . |
| .\" HTML <a name="localesupport"></a> |
| .SH "LOCALE SUPPORT" |
| .rs |
| .sp |
| PCRE handles caseless matching, and determines whether characters are letters, |
| digits, or whatever, by reference to a set of tables, indexed by character |
| value. When running in UTF-8 mode, this applies only to characters with codes |
| less than 128. By default, higher-valued codes never match escapes such as \ew |
| or \ed, but they can be tested with \ep if PCRE is built with Unicode character |
| property support. Alternatively, the PCRE_UCP option can be set at compile |
| time; this causes \ew and friends to use Unicode property support instead of |
| built-in tables. The use of locales with Unicode is discouraged. If you are |
| handling characters with codes greater than 128, you should either use UTF-8 |
| and Unicode, or use locales, but not try to mix the two. |
| .P |
| PCRE contains an internal set of tables that are used when the final argument |
| of \fBpcre_compile()\fP is NULL. These are sufficient for many applications. |
| Normally, the internal tables recognize only ASCII characters. However, when |
| PCRE 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 always be overridden by tables supplied by the |
| application that calls PCRE. 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 \fBpcre_maketables()\fP function, |
| which has no arguments, in the relevant locale. The result can then be passed |
| to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. 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 = pcre_maketables(); |
| re = pcre_compile(..., tables); |
| .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". |
| .P |
| When \fBpcre_maketables()\fP runs, the tables are built in memory that is |
| obtained via \fBpcre_malloc\fP. 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 to \fBpcre_compile()\fP is saved with the compiled |
| pattern, and the same tables are used via this pointer by \fBpcre_study()\fP |
| and normally also by \fBpcre_exec()\fP. Thus, by default, for any single |
| pattern, compilation, studying and matching all happen in the same locale, but |
| different patterns can be compiled in different locales. |
| .P |
| It is possible to pass a table pointer or NULL (indicating the use of the |
| internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose, |
| this facility could be used to match a pattern in a different locale from the |
| one in which it was compiled. Passing table pointers at run time is discussed |
| below in the section on matching a pattern. |
| . |
| . |
| .\" HTML <a name="infoaboutpattern"></a> |
| .SH "INFORMATION ABOUT A PATTERN" |
| .rs |
| .sp |
| .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," |
| .ti +5n |
| .B int \fIwhat\fP, void *\fIwhere\fP); |
| .PP |
| The \fBpcre_fullinfo()\fP function returns information about a compiled |
| pattern. It replaces the obsolete \fBpcre_info()\fP function, which is |
| nevertheless retained for backwards compability (and is documented below). |
| .P |
| The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled |
| pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if |
| the pattern was not studied. The third argument specifies which piece of |
| information is required, and the fourth 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 |
| PCRE_ERROR_NULL the argument \fIcode\fP was NULL |
| the argument \fIwhere\fP was NULL |
| PCRE_ERROR_BADMAGIC the "magic number" was not found |
| PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid |
| .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 |
| \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern: |
| .sp |
| int rc; |
| size_t length; |
| rc = pcre_fullinfo( |
| re, /* result of pcre_compile() */ |
| sd, /* result of pcre_study(), or NULL */ |
| PCRE_INFO_SIZE, /* what is required */ |
| &length); /* where to put the data */ |
| .sp |
| The possible values for the third argument are defined in \fBpcre.h\fP, and are |
| as follows: |
| .sp |
| PCRE_INFO_BACKREFMAX |
| .sp |
| Return the number of the highest back reference in the pattern. The fourth |
| argument should point to an \fBint\fP variable. Zero is returned if there are |
| no back references. |
| .sp |
| PCRE_INFO_CAPTURECOUNT |
| .sp |
| Return the number of capturing subpatterns in the pattern. The fourth argument |
| should point to an \fBint\fP variable. |
| .sp |
| PCRE_INFO_DEFAULT_TABLES |
| .sp |
| Return a pointer to the internal default character tables within PCRE. The |
| fourth argument should point to an \fBunsigned char *\fP variable. This |
| information call is provided for internal use by the \fBpcre_study()\fP |
| function. External callers can cause PCRE to use its internal tables by passing |
| a NULL table pointer. |
| .sp |
| PCRE_INFO_FIRSTBYTE |
| .sp |
| Return information about the first byte of any matched string, for a |
| non-anchored pattern. The fourth argument should point to an \fBint\fP |
| variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is |
| still recognized for backwards compatibility.) |
| .P |
| If there is a fixed first byte, for example, from a pattern such as |
| (cat|cow|coyote), its value is returned. Otherwise, if either |
| .sp |
| (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch |
| starts with "^", or |
| .sp |
| (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set |
| (if it were set, the pattern would be anchored), |
| .sp |
| -1 is returned, indicating that the pattern matches only at the start of a |
| subject string or after any newline within the string. Otherwise -2 is |
| returned. For anchored patterns, -2 is returned. |
| .sp |
| PCRE_INFO_FIRSTTABLE |
| .sp |
| If the pattern was studied, and this resulted in the construction of a 256-bit |
| table indicating a fixed set of bytes for the first byte in any matching |
| string, a pointer to the table is returned. Otherwise NULL is returned. The |
| fourth argument should point to an \fBunsigned char *\fP variable. |
| .sp |
| PCRE_INFO_HASCRORLF |
| .sp |
| Return 1 if the pattern contains any explicit matches for CR or LF characters, |
| otherwise 0. The fourth argument should point to an \fBint\fP variable. An |
| explicit match is either a literal CR or LF character, or \er or \en. |
| .sp |
| PCRE_INFO_JCHANGED |
| .sp |
| Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise |
| 0. The fourth argument should point to an \fBint\fP variable. (?J) and |
| (?-J) set and unset the local PCRE_DUPNAMES option, respectively. |
| .sp |
| PCRE_INFO_JIT |
| .sp |
| Return 1 if the pattern was studied with the PCRE_STUDY_JIT_COMPILE option, and |
| just-in-time compiling was successful. The fourth argument should point to an |
| \fBint\fP variable. A return value of 0 means that JIT support is not available |
| in this version of PCRE, or that the pattern was not studied with the |
| PCRE_STUDY_JIT_COMPILE option, or that the JIT compiler could not handle this |
| particular pattern. See the |
| .\" HREF |
| \fBpcrejit\fP |
| .\" |
| documentation for details of what can and cannot be handled. |
| .sp |
| PCRE_INFO_JITSIZE |
| .sp |
| If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option, |
| return the size of the JIT compiled code, otherwise return zero. The fourth |
| argument should point to a \fBsize_t\fP variable. |
| .sp |
| PCRE_INFO_LASTLITERAL |
| .sp |
| Return the value of the rightmost literal byte that must exist in any matched |
| string, other than at its start, if such a byte has been recorded. The fourth |
| argument should point to an \fBint\fP variable. If there is no such byte, -1 is |
| returned. For anchored patterns, a last literal byte is recorded only if it |
| follows something of variable length. For example, for the pattern |
| /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value |
| is -1. |
| .sp |
| PCRE_INFO_MINLENGTH |
| .sp |
| If the pattern was studied and a minimum length for matching subject strings |
| was computed, its value is returned. Otherwise the returned value is -1. The |
| value is a number of characters, not bytes (this may be relevant in UTF-8 |
| mode). The fourth argument should point to an \fBint\fP variable. A |
| non-negative 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 |
| PCRE_INFO_NAMECOUNT |
| PCRE_INFO_NAMEENTRYSIZE |
| PCRE_INFO_NAMETABLE |
| .sp |
| PCRE 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 |
| \fBpcre_get_named_substring()\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 \fBpcre_exec()\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. PCRE_INFO_NAMECOUNT gives |
| the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each |
| entry; both of these return an \fBint\fP value. The entry size depends on the |
| length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first |
| entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry |
| are the number of the capturing parenthesis, most significant byte first. The |
| rest of the entry is the corresponding name, zero terminated. |
| .P |
| The names are in alphabetical order. Duplicate names may appear if (?| is used |
| to create multiple groups with the same number, as described in the |
| .\" HTML <a href="pcrepattern.html#dupsubpatternnumber"> |
| .\" </a> |
| section on duplicate subpattern numbers |
| .\" |
| in the |
| .\" HREF |
| \fBpcrepattern\fP |
| .\" |
| page. Duplicate names for subpatterns with different numbers are permitted only |
| if PCRE_DUPNAMES is set. In all cases of duplicate names, 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 |
| (assume PCRE_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 |
| PCRE_INFO_OKPARTIAL |
| .sp |
| Return 1 if the pattern can be used for partial matching with |
| \fBpcre_exec()\fP, otherwise 0. The fourth argument should point to an |
| \fBint\fP variable. From release 8.00, this always returns 1, because the |
| restrictions that previously applied to partial matching have been lifted. The |
| .\" HREF |
| \fBpcrepartial\fP |
| .\" |
| documentation gives details of partial matching. |
| .sp |
| PCRE_INFO_OPTIONS |
| .sp |
| Return a copy of the options with which the pattern was compiled. The fourth |
| argument should point to an \fBunsigned long int\fP variable. These option bits |
| are those specified in the call to \fBpcre_compile()\fP, 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 PCRE_EXTENDED option, the |
| result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. |
| .P |
| A pattern is automatically anchored by PCRE if all of its top-level |
| alternatives begin with one of the following: |
| .sp |
| ^ unless PCRE_MULTILINE is set |
| \eA always |
| \eG always |
| .\" JOIN |
| .* if PCRE_DOTALL is set and there are no back |
| references to the subpattern in which .* appears |
| .sp |
| For such patterns, the PCRE_ANCHORED bit is set in the options returned by |
| \fBpcre_fullinfo()\fP. |
| .sp |
| PCRE_INFO_SIZE |
| .sp |
| Return the size of the compiled pattern. The fourth argument should point to a |
| \fBsize_t\fP variable. This value does not include the size of the \fBpcre\fP |
| structure that is returned by \fBpcre_compile()\fP. The value that is passed as |
| the argument to \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory |
| in which to place the compiled data is the value returned by this option plus |
| the size of the \fBpcre\fP structure. Studying a compiled pattern, with or |
| without JIT, does not alter the value returned by this option. |
| .sp |
| PCRE_INFO_STUDYSIZE |
| .sp |
| Return the size of the data block pointed to by the \fIstudy_data\fP field in a |
| \fBpcre_extra\fP block. If \fBpcre_extra\fP is NULL, or there is no study data, |
| zero is returned. The fourth argument should point to a \fBsize_t\fP variable. |
| The \fIstudy_data\fP field is set by \fBpcre_study()\fP to record information |
| that will speed up matching (see the section entitled |
| .\" HTML <a href="#studyingapattern"> |
| .\" </a> |
| "Studying a pattern" |
| .\" |
| above). The format of the \fIstudy_data\fP block is private, but its length |
| is made available via this option so that it can be saved and restored (see the |
| .\" HREF |
| \fBpcreprecompile\fP |
| .\" |
| documentation for details). |
| . |
| . |
| .SH "OBSOLETE INFO FUNCTION" |
| .rs |
| .sp |
| .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int |
| .B *\fIfirstcharptr\fP); |
| .PP |
| The \fBpcre_info()\fP function is now obsolete because its interface is too |
| restrictive to return all the available data about a compiled pattern. New |
| programs should use \fBpcre_fullinfo()\fP instead. The yield of |
| \fBpcre_info()\fP is the number of capturing subpatterns, or one of the |
| following negative numbers: |
| .sp |
| PCRE_ERROR_NULL the argument \fIcode\fP was NULL |
| PCRE_ERROR_BADMAGIC the "magic number" was not found |
| .sp |
| If the \fIoptptr\fP argument is not NULL, a copy of the options with which the |
| pattern was compiled is placed in the integer it points to (see |
| PCRE_INFO_OPTIONS above). |
| .P |
| If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL, |
| it is used to pass back information about the first character of any matched |
| string (see PCRE_INFO_FIRSTBYTE above). |
| . |
| . |
| .SH "REFERENCE COUNTS" |
| .rs |
| .sp |
| .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); |
| .PP |
| The \fBpcre_refcount()\fP function is used to maintain a reference count in the |
| data block that contains a compiled pattern. It is provided for the benefit of |
| applications that operate in an object-oriented manner, where different parts |
| of the application may be using the same compiled pattern, but you want to free |
| the block when they are all done. |
| .P |
| When a pattern is compiled, the reference count field is initialized to zero. |
| It is changed only by calling this function, whose action is to add the |
| \fIadjust\fP value (which may be positive or negative) to it. The yield of the |
| function is the new value. However, the value of the count is constrained to |
| lie between 0 and 65535, inclusive. If the new value is outside these limits, |
| it is forced to the appropriate limit value. |
| .P |
| Except when it is zero, the reference count is not correctly preserved if a |
| pattern is compiled on one host and then transferred to a host whose byte-order |
| is different. (This seems a highly unlikely scenario.) |
| . |
| . |
| .SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION" |
| .rs |
| .sp |
| .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," |
| .ti +5n |
| .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, |
| .ti +5n |
| .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); |
| .P |
| The function \fBpcre_exec()\fP is called to match a subject string against a |
| compiled pattern, which is passed in the \fIcode\fP argument. If the |
| pattern was studied, the result of the study should be passed in the |
| \fIextra\fP argument. You can call \fBpcre_exec()\fP with the same \fIcode\fP |
| and \fIextra\fP arguments as many times as you like, in order 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 \fBpcre_dfa_exec()\fP function. |
| .P |
| In most applications, the pattern will have been compiled (and optionally |
| studied) in the same process that calls \fBpcre_exec()\fP. However, it is |
| possible to save compiled patterns and study data, and then use them later |
| in different processes, possibly even on different hosts. For a discussion |
| about this, see the |
| .\" HREF |
| \fBpcreprecompile\fP |
| .\" |
| documentation. |
| .P |
| Here is an example of a simple call to \fBpcre_exec()\fP: |
| .sp |
| int rc; |
| int ovector[30]; |
| rc = pcre_exec( |
| re, /* result of pcre_compile() */ |
| NULL, /* we didn't study the pattern */ |
| "some string", /* the subject string */ |
| 11, /* the length of the subject string */ |
| 0, /* start at offset 0 in the subject */ |
| 0, /* default options */ |
| ovector, /* vector of integers for substring information */ |
| 30); /* number of elements (NOT size in bytes) */ |
| . |
| . |
| .\" HTML <a name="extradata"></a> |
| .SS "Extra data for \fBpcre_exec()\fR" |
| .rs |
| .sp |
| If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP |
| data block. The \fBpcre_study()\fP function returns such a block (when it |
| doesn't return NULL), but you can also create one for yourself, and pass |
| additional information in it. The \fBpcre_extra\fP block contains the following |
| fields (not necessarily in this order): |
| .sp |
| unsigned long int \fIflags\fP; |
| void *\fIstudy_data\fP; |
| void *\fIexecutable_jit\fP; |
| unsigned long int \fImatch_limit\fP; |
| unsigned long int \fImatch_limit_recursion\fP; |
| void *\fIcallout_data\fP; |
| const unsigned char *\fItables\fP; |
| unsigned char **\fImark\fP; |
| .sp |
| The \fIflags\fP field is a bitmap that specifies which of the other fields |
| are set. The flag bits are: |
| .sp |
| PCRE_EXTRA_STUDY_DATA |
| PCRE_EXTRA_EXECUTABLE_JIT |
| PCRE_EXTRA_MATCH_LIMIT |
| PCRE_EXTRA_MATCH_LIMIT_RECURSION |
| PCRE_EXTRA_CALLOUT_DATA |
| PCRE_EXTRA_TABLES |
| PCRE_EXTRA_MARK |
| .sp |
| Other flag bits should be set to zero. The \fIstudy_data\fP field and sometimes |
| the \fIexecutable_jit\fP field are set in the \fBpcre_extra\fP block that is |
| returned by \fBpcre_study()\fP, together with the appropriate flag bits. You |
| should not set these yourself, but you may add to the block by setting the |
| other fields and their corresponding flag bits. |
| .P |
| The \fImatch_limit\fP field provides a means of preventing PCRE from using up a |
| vast amount of resources when running 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, \fBpcre_exec()\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. |
| .P |
| When \fBpcre_exec()\fP is called with a pattern that was successfully studied |
| with the PCRE_STUDY_JIT_COMPILE option, 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 PCRE is built; the default |
| default is 10 million, which handles all but the most extreme cases. You can |
| override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP |
| block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in |
| the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns |
| PCRE_ERROR_MATCHLIMIT. |
| .P |
| The \fImatch_limit_recursion\fP field 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 machine stack that can be |
| used, or, when PCRE 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, if the pattern was successfully studied with |
| PCRE_STUDY_JIT_COMPILE. |
| .P |
| The default value for \fImatch_limit_recursion\fP can be set when PCRE is |
| built; the default default is the same value as the default for |
| \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP |
| with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and |
| PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit |
| is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT. |
| .P |
| The \fIcallout_data\fP field is used in conjunction with the "callout" feature, |
| and is described in the |
| .\" HREF |
| \fBpcrecallout\fP |
| .\" |
| documentation. |
| .P |
| The \fItables\fP field is used to pass a character tables pointer to |
| \fBpcre_exec()\fP; this overrides the value that is stored with the compiled |
| pattern. A non-NULL value is stored with the compiled pattern only if custom |
| tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument. |
| If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's |
| internal tables to be used. This facility is helpful when re-using patterns |
| that have been saved after compiling with an external set of tables, because |
| the external tables might be at a different address when \fBpcre_exec()\fP is |
| called. See the |
| .\" HREF |
| \fBpcreprecompile\fP |
| .\" |
| documentation for a discussion of saving compiled patterns for later use. |
| .P |
| If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must |
| be set to point to a \fBchar *\fP variable. If the pattern contains any |
| backtracking control verbs such as (*MARK:NAME), and the execution ends up with |
| a name to pass back, a pointer to the name string (zero terminated) is placed |
| in the variable pointed to by the \fImark\fP field. The names are within the |
| compiled pattern; if you wish to retain such a name you must copy it before |
| freeing the memory of a compiled pattern. If there is no name to pass back, the |
| variable pointed to by the \fImark\fP field set to NULL. For details of the |
| backtracking control verbs, see the section entitled |
| .\" HTML <a href="pcrepattern#backtrackcontrol"> |
| .\" </a> |
| "Backtracking control" |
| .\" |
| in the |
| .\" HREF |
| \fBpcrepattern\fP |
| .\" |
| documentation. |
| . |
| . |
| .\" HTML <a name="execoptions"></a> |
| .SS "Option bits for \fBpcre_exec()\fP" |
| .rs |
| .sp |
| The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be |
| zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, |
| PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, |
| PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and |
| PCRE_PARTIAL_HARD. |
| .P |
| If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option, |
| the only supported options for JIT execution are PCRE_NO_UTF8_CHECK, |
| PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NOTEMPTY_ATSTART. Note in |
| particular that partial matching is not supported. If an unsupported option is |
| used, JIT execution is disabled and the normal interpretive code in |
| \fBpcre_exec()\fP is run. |
| .sp |
| PCRE_ANCHORED |
| .sp |
| The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first |
| matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out |
| to be anchored by virtue of its contents, it cannot be made unachored at |
| matching time. |
| .sp |
| PCRE_BSR_ANYCRLF |
| PCRE_BSR_UNICODE |
| .sp |
| These options (which are mutually exclusive) control what the \eR escape |
| sequence matches. The choice is either to match only CR, LF, or CRLF, or to |
| match any Unicode newline sequence. These options override the choice that was |
| made or defaulted when the pattern was compiled. |
| .sp |
| PCRE_NEWLINE_CR |
| PCRE_NEWLINE_LF |
| PCRE_NEWLINE_CRLF |
| PCRE_NEWLINE_ANYCRLF |
| PCRE_NEWLINE_ANY |
| .sp |
| These options override the newline definition that was chosen or defaulted when |
| the pattern was compiled. For details, see the description of |
| \fBpcre_compile()\fP above. 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 PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_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 PCRE_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, 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. |
| .sp |
| PCRE_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 PCRE_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 |
| PCRE_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 PCRE_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 |
| PCRE_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 PCRE_NOTEMPTY set, this match is not |
| valid, so PCRE searches further into the string for occurrences of "a" or "b". |
| .sp |
| PCRE_NOTEMPTY_ATSTART |
| .sp |
| This is like PCRE_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. |
| .P |
| Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it |
| does make a special case of a pattern match of the empty string within its |
| \fBsplit()\fP function, and when using the /g modifier. It is possible to |
| emulate Perl's behaviour after matching a null string by first trying the match |
| again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then |
| if that fails, by advancing the starting offset (see below) and trying an |
| ordinary match again. There is some code that demonstrates how to do this in |
| the |
| .\" HREF |
| \fBpcredemo\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. |
| .sp |
| PCRE_NO_START_OPTIMIZE |
| .sp |
| There are a number of optimizations that \fBpcre_exec()\fP uses 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, it 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. 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 PCRE_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. If |
| PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching |
| time. |
| .P |
| Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation. |
| Consider the pattern |
| .sp |
| (*COMMIT)ABC |
| .sp |
| When this is compiled, PCRE 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 PCRE_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". If the pattern is studied, more start-up |
| optimizations may be used. 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", "C", and then finally an empty string. |
| If the pattern is studied, the final attempt does not take place, because PCRE |
| knows that the subject is too short, and so the (*MARK) is never encountered. |
| In this case, studying the pattern does not affect the overall match result, |
| which is still "no match", but it does affect the auxiliary information that is |
| returned. |
| .sp |
| PCRE_NO_UTF8_CHECK |
| .sp |
| When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 |
| string is automatically checked when \fBpcre_exec()\fP is subsequently called. |
| The value of \fIstartoffset\fP is also checked to ensure that it points to the |
| start of a UTF-8 character. There is a discussion about the validity of UTF-8 |
| strings in the |
| .\" HTML <a href="pcre.html#utf8strings"> |
| .\" </a> |
| section on UTF-8 support |
| .\" |
| in the main |
| .\" HREF |
| \fBpcre\fP |
| .\" |
| page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns |
| the error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is |
| a truncated UTF-8 character at the end of the subject, PCRE_ERROR_SHORTUTF8. In |
| both cases, information about the precise nature of the error may also be |
| returned (see the descriptions of these errors in the section entitled \fIError |
| return values from\fP \fBpcre_exec()\fP |
| .\" HTML <a href="#errorlist"> |
| .\" </a> |
| below). |
| .\" |
| If \fIstartoffset\fP contains a value that does not point to the start of a |
| UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is |
| returned. |
| .P |
| If you already know that your subject is valid, and you want to skip these |
| checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when |
| calling \fBpcre_exec()\fP. You might want to do this for the second and |
| subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find |
| all the matches in a single subject string. However, you should be sure that |
| the value of \fIstartoffset\fP points to the start of a UTF-8 character (or the |
| end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an |
| invalid UTF-8 string as a subject or an invalid value of \fIstartoffset\fP is |
| undefined. Your program may crash. |
| .sp |
| PCRE_PARTIAL_HARD |
| PCRE_PARTIAL_SOFT |
| .sp |
| These options turn on the partial matching feature. For backwards |
| compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. 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 |
| PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by |
| testing any remaining alternatives. Only if no complete match can be found is |
| PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words, |
| PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match, |
| but only if no complete match can be found. |
| .P |
| If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a |
| partial match is found, \fBpcre_exec()\fP immediately returns |
| PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words, |
| when PCRE_PARTIAL_HARD is set, a partial match is considered to be more |
| important that an alternative complete match. |
| .P |
| In both cases, the portion of the string that was inspected when the partial |
| match was found is set as the first matching string. There is a more detailed |
| discussion of partial and multi-segment matching, with examples, in the |
| .\" HREF |
| \fBpcrepartial\fP |
| .\" |
| documentation. |
| . |
| . |
| .SS "The string to be matched by \fBpcre_exec()\fP" |
| .rs |
| .sp |
| The subject string is passed to \fBpcre_exec()\fP as a pointer in |
| \fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset |
| in \fIstartoffset\fP. If this is negative or greater than the length of the |
| subject, \fBpcre_exec()\fP returns PCRE_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 mode, the byte offset must |
| point to the start of a UTF-8 character (or the end of the subject). Unlike the |
| pattern string, the subject may contain binary zero bytes. |
| .P |
| A non-zero starting offset is useful when searching for another match in the |
| same subject by calling \fBpcre_exec()\fP again after a previous success. |
| Setting \fIstartoffset\fP differs from just passing over a shortened string and |
| setting PCRE_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 \fBpcre_exec()\fP finds the first |
| occurrence. If \fBpcre_exec()\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 |
| \fBpcre_exec()\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 PCRE_NOTEMPTY_ATSTART and |
| PCRE_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 |
| \fBpcredemo\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. |
| . |
| . |
| .SS "How \fBpcre_exec()\fP returns captured substrings" |
| .rs |
| .sp |
| In general, a pattern matches a certain portion of the subject, and in |
| addition, further substrings from the subject may be picked out by 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. PCRE supports several other |
| kinds of parenthesized subpattern that do not cause substrings to be captured. |
| .P |
| Captured substrings are returned to the caller via a vector of integers whose |
| address is passed in \fIovector\fP. The number of elements in the vector is |
| passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this |
| argument is NOT the size of \fIovector\fP in bytes. |
| .P |
| The first two-thirds of the vector is used to pass back captured substrings, |
| each substring using a pair of integers. The remaining third of the vector is |
| used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns, |
| and is not available for passing back information. The number passed in |
| \fIovecsize\fP should always be a multiple of three. If it is not, it is |
| rounded down. |
| .P |
| When a match is successful, information about captured substrings is returned |
| in pairs of integers, starting at the beginning of \fIovector\fP, and |
| continuing up to two-thirds of its length at the most. The first element of |
| each pair is set to the byte offset of the first character in a substring, and |
| the second is set to the byte offset of the first character after the end of a |
| substring. \fBNote\fP: these values are always byte offsets, even in UTF-8 |
| mode. They are not character counts. |
| .P |
| The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the |
| portion of the subject string matched by the entire pattern. The next pair is |
| used for the first capturing subpattern, and so on. The value returned by |
| \fBpcre_exec()\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, it is the last portion of the |
| string that it matched that is returned. |
| .P |
| If the vector is too small to hold all the captured substring offsets, it is |
| used as far as possible (up to two-thirds of its length), and the function |
| returns a value of zero. If neither the actual string matched not any captured |
| substrings are of interest, \fBpcre_exec()\fP may be called with \fIovector\fP |
| passed as NULL and \fIovecsize\fP as zero. However, if the pattern contains |
| back references and the \fIovector\fP is not big enough to remember the related |
| substrings, PCRE has to get additional memory for use during matching. Thus it |
| is usually advisable to supply an \fIovector\fP of reasonable size. |
| .P |
| There are some cases where zero is returned (indicating vector overflow) when |
| in fact the vector is exactly the right size for the final match. For example, |
| consider the pattern |
| .sp |
| (a)(?:(b)c|bd) |
| .sp |
| If a vector of 6 elements (allowing for only 1 captured substring) is given |
| with subject string "abd", \fBpcre_exec()\fP will try to set the second |
| captured string, thereby recording a vector overflow, before failing to match |
| "c" and backing up to try the second alternative. The zero return, however, |
| does correctly indicate that the maximum number of slots (namely 2) have been |
| filled. In similar cases where there is temporary overflow, but the final |
| number of used slots is actually less than the maximum, a non-zero value is |
| returned. |
| .P |
| The \fBpcre_fullinfo()\fP function can be used to find out how many capturing |
| subpatterns there are in a compiled pattern. The smallest size for |
| \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to |
| the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3. |
| .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 -1. |
| .P |
| Offset values that correspond to unused subpatterns at the end of the |
| expression are also set to -1. 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, and the offsets for for the second and third capturing subpatterns |
| (assuming the vector is large enough, of course) are set to -1. |
| .P |
| \fBNote\fP: Elements in the first two-thirds of \fIovector\fP 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 \fBpcre_exec()\fP. The other |
| elements (in the first two-thirds) retain whatever values they previously had. |
| .P |
| Some convenience functions are provided for extracting the captured substrings |
| as separate strings. These are described below. |
| . |
| . |
| .\" HTML <a name="errorlist"></a> |
| .SS "Error return values from \fBpcre_exec()\fP" |
| .rs |
| .sp |
| If \fBpcre_exec()\fP fails, it returns a negative number. The following are |
| defined in the header file: |
| .sp |
| PCRE_ERROR_NOMATCH (-1) |
| .sp |
| The subject string did not match the pattern. |
| .sp |
| PCRE_ERROR_NULL (-2) |
| .sp |
| Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was |
| NULL and \fIovecsize\fP was not zero. |
| .sp |
| PCRE_ERROR_BADOPTION (-3) |
| .sp |
| An unrecognized bit was set in the \fIoptions\fP argument. |
| .sp |
| PCRE_ERROR_BADMAGIC (-4) |
| .sp |
| PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch |
| the case when it is passed a junk pointer and to detect when a pattern that was |
| compiled in an environment of one endianness is run in an environment with the |
| other endianness. This is the error that PCRE gives when the magic number is |
| not present. |
| .sp |
| PCRE_ERROR_UNKNOWN_OPCODE (-5) |
| .sp |
| While running the pattern match, an unknown item was encountered in the |
| compiled pattern. This error could be caused by a bug in PCRE or by overwriting |
| of the compiled pattern. |
| .sp |
| PCRE_ERROR_NOMEMORY (-6) |
| .sp |
| If a pattern contains back references, but the \fIovector\fP that is passed to |
| \fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE |
| gets a block of memory at the start of matching to use for this purpose. If the |
| call via \fBpcre_malloc()\fP fails, this error is given. The memory is |
| automatically freed at the end of matching. |
| .P |
| This error is also given if \fBpcre_stack_malloc()\fP fails in |
| \fBpcre_exec()\fP. This can happen only when PCRE has been compiled with |
| \fB--disable-stack-for-recursion\fP. |
| .sp |
| PCRE_ERROR_NOSUBSTRING (-7) |
| .sp |
| This error is used by the \fBpcre_copy_substring()\fP, |
| \fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see |
| below). It is never returned by \fBpcre_exec()\fP. |
| .sp |
| PCRE_ERROR_MATCHLIMIT (-8) |
| .sp |
| The backtracking limit, as specified by the \fImatch_limit\fP field in a |
| \fBpcre_extra\fP structure (or defaulted) was reached. See the description |
| above. |
| .sp |
| PCRE_ERROR_CALLOUT (-9) |
| .sp |
| This error is never generated by \fBpcre_exec()\fP itself. It is provided for |
| use by callout functions that want to yield a distinctive error code. See the |
| .\" HREF |
| \fBpcrecallout\fP |
| .\" |
| documentation for details. |
| .sp |
| PCRE_ERROR_BADUTF8 (-10) |
| .sp |
| A string that contains an invalid UTF-8 byte sequence was passed as a subject, |
| and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector |
| (\fIovecsize\fP) is at least 2, the byte offset to the start of the the invalid |
| UTF-8 character is placed in the first element, and a reason code is placed in |
| the second element. The reason codes are listed in the |
| .\" HTML <a href="#badutf8reasons"> |
| .\" </a> |
| following section. |
| .\" |
| For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a |
| truncated UTF-8 character at the end of the subject (reason codes 1 to 5), |
| PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8. |
| .sp |
| PCRE_ERROR_BADUTF8_OFFSET (-11) |
| .sp |
| The UTF-8 byte sequence that was passed as a subject was checked and found to |
| be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of |
| \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the |
| end of the subject. |
| .sp |
| PCRE_ERROR_PARTIAL (-12) |
| .sp |
| The subject string did not match, but it did match partially. See the |
| .\" HREF |
| \fBpcrepartial\fP |
| .\" |
| documentation for details of partial matching. |
| .sp |
| PCRE_ERROR_BADPARTIAL (-13) |
| .sp |
| This code is no longer in use. It was formerly returned when the PCRE_PARTIAL |
| option was used with a compiled pattern containing items that were not |
| supported for partial matching. From release 8.00 onwards, there are no |
| restrictions on partial matching. |
| .sp |
| PCRE_ERROR_INTERNAL (-14) |
| .sp |
| An unexpected internal error has occurred. This error could be caused by a bug |
| in PCRE or by overwriting of the compiled pattern. |
| .sp |
| PCRE_ERROR_BADCOUNT (-15) |
| .sp |
| This error is given if the value of the \fIovecsize\fP argument is negative. |
| .sp |
| PCRE_ERROR_RECURSIONLIMIT (-21) |
| .sp |
| The internal recursion limit, as specified by the \fImatch_limit_recursion\fP |
| field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the |
| description above. |
| .sp |
| PCRE_ERROR_BADNEWLINE (-23) |
| .sp |
| An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given. |
| .sp |
| PCRE_ERROR_BADOFFSET (-24) |
| .sp |
| The value of \fIstartoffset\fP was negative or greater than the length of the |
| subject, that is, the value in \fIlength\fP. |
| .sp |
| PCRE_ERROR_SHORTUTF8 (-25) |
| .sp |
| This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string |
| ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set. |
| Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in |
| fact sufficient to detect this case, but this special error code for |
| PCRE_PARTIAL_HARD precedes the implementation of returned information; it is |
| retained for backwards compatibility. |
| .sp |
| PCRE_ERROR_RECURSELOOP (-26) |
| .sp |
| This error is returned when \fBpcre_exec()\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 |
| PCRE_ERROR_JIT_STACKLIMIT (-27) |
| .sp |
| This error is returned when a pattern that was successfully studied using the |
| PCRE_STUDY_JIT_COMPILE option is being matched, but the memory available for |
| the just-in-time processing stack is not large enough. See the |
| .\" HREF |
| \fBpcrejit\fP |
| .\" |
| documentation for more details. |
| .P |
| Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP. |
| . |
| . |
| .\" HTML <a name="badutf8reasons"></a> |
| .SS "Reason codes for invalid UTF-8 strings" |
| .rs |
| .sp |
| When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or |
| PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at |
| least 2, the offset of the start of the invalid UTF-8 character is placed in |
| the first output vector element (\fIovector[0]\fP) and a reason code is placed |
| in the second element (\fIovector[1]\fP). The reason codes are given names in |
| the \fBpcre.h\fP header file: |
| .sp |
| PCRE_UTF8_ERR1 |
| PCRE_UTF8_ERR2 |
| PCRE_UTF8_ERR3 |
| PCRE_UTF8_ERR4 |
| PCRE_UTF8_ERR5 |
| .sp |
| The string ends with a truncated UTF-8 character; the code specifies how many |
| bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be |
| no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279) |
| allows for up to 6 bytes, and this is checked first; hence the possibility of |
| 4 or 5 missing bytes. |
| .sp |
| PCRE_UTF8_ERR6 |
| PCRE_UTF8_ERR7 |
| PCRE_UTF8_ERR8 |
| PCRE_UTF8_ERR9 |
| PCRE_UTF8_ERR10 |
| .sp |
| The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the |
| character do not have the binary value 0b10 (that is, either the most |
| significant bit is 0, or the next bit is 1). |
| .sp |
| PCRE_UTF8_ERR11 |
| PCRE_UTF8_ERR12 |
| .sp |
| A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long; |
| these code points are excluded by RFC 3629. |
| .sp |
| PCRE_UTF8_ERR13 |
| .sp |
| A 4-byte character has a value greater than 0x10fff; these code points are |
| excluded by RFC 3629. |
| .sp |
| PCRE_UTF8_ERR14 |
| .sp |
| A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of |
| code points are reserved by RFC 3629 for use with UTF-16, and so are excluded |
| from UTF-8. |
| .sp |
| PCRE_UTF8_ERR15 |
| PCRE_UTF8_ERR16 |
| PCRE_UTF8_ERR17 |
| PCRE_UTF8_ERR18 |
| PCRE_UTF8_ERR19 |
| .sp |
| A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a |
| value that can be represented by fewer bytes, which is invalid. For example, |
| the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just |
| one byte. |
| .sp |
| PCRE_UTF8_ERR20 |
| .sp |
| The two most significant bits of the first byte of a character have the binary |
| value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a |
| byte can only validly occur as the second or subsequent byte of a multi-byte |
| character. |
| .sp |
| PCRE_UTF8_ERR21 |
| .sp |
| The first byte of a character has the value 0xfe or 0xff. These values can |
| never occur in a valid UTF-8 string. |
| . |
| . |
| .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER" |
| .rs |
| .sp |
| .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, |
| .ti +5n |
| .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, |
| .ti +5n |
| .B int \fIbuffersize\fP); |
| .PP |
| .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, |
| .ti +5n |
| .B int \fIstringcount\fP, int \fIstringnumber\fP, |
| .ti +5n |
| .B const char **\fIstringptr\fP); |
| .PP |
| .B int pcre_get_substring_list(const char *\fIsubject\fP, |
| .ti +5n |
| .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" |
| .PP |
| Captured substrings can be accessed directly by using the offsets returned by |
| \fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions |
| \fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and |
| \fBpcre_get_substring_list()\fP are provided for extracting captured substrings |
| as new, separate, zero-terminated strings. These functions identify substrings |
| by number. The next section describes functions for extracting named |
| substrings. |
| .P |
| 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. |
| However, you can process such a string by referring to the length that is |
| returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP. |
| Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate |
| for handling strings containing binary zeros, because the end of the final |
| string is not independently indicated. |
| .P |
| The first three arguments are the same for all three of these functions: |
| \fIsubject\fP is the subject string that has just been successfully matched, |
| \fIovector\fP is a pointer to the vector of integer offsets that was passed to |
| \fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were |
| captured by the match, including the substring that matched the entire regular |
| expression. This is the value returned by \fBpcre_exec()\fP if it is greater |
| than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of |
| space in \fIovector\fP, the value passed as \fIstringcount\fP should be the |
| number of elements in the vector divided by three. |
| .P |
| The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP |
| extract a single substring, whose number is given as \fIstringnumber\fP. A |
| value of zero extracts the substring that matched the entire pattern, whereas |
| higher values extract the captured substrings. For \fBpcre_copy_substring()\fP, |
| the string is placed in \fIbuffer\fP, whose length is given by |
| \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is |
| obtained via \fBpcre_malloc\fP, and its address is returned via |
| \fIstringptr\fP. The yield of the function is the length of the string, not |
| including the terminating zero, or one of these error codes: |
| .sp |
| PCRE_ERROR_NOMEMORY (-6) |
| .sp |
| The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get |
| memory failed for \fBpcre_get_substring()\fP. |
| .sp |
| PCRE_ERROR_NOSUBSTRING (-7) |
| .sp |
| There is no substring whose number is \fIstringnumber\fP. |
| .P |
| The \fBpcre_get_substring_list()\fP function extracts all available substrings |
| and builds a list of pointers to them. All this is done in a single block of |
| memory that is obtained via \fBpcre_malloc\fP. 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 yield of the |
| function is zero if all went well, or the error code |
| .sp |
| PCRE_ERROR_NOMEMORY (-6) |
| .sp |
| if the attempt to get the memory block failed. |
| .P |
| When any of these functions encounter 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, they return an empty |
| string. This can be distinguished from a genuine zero-length substring by |
| inspecting the appropriate offset in \fIovector\fP, which is negative for unset |
| substrings. |
| .P |
| The two convenience functions \fBpcre_free_substring()\fP and |
| \fBpcre_free_substring_list()\fP can be used to free the memory returned by |
| a previous call of \fBpcre_get_substring()\fP or |
| \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call |
| the function pointed to by \fBpcre_free\fP, which of course could be called |
| directly from a C program. However, PCRE is used in some situations where it is |
| linked via a special interface to another programming language that cannot use |
| \fBpcre_free\fP directly; it is for these cases that the functions are |
| provided. |
| . |
| . |
| .SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME" |
| .rs |
| .sp |
| .B int pcre_get_stringnumber(const pcre *\fIcode\fP, |
| .ti +5n |
| .B const char *\fIname\fP); |
| .PP |
| .B int pcre_copy_named_substring(const pcre *\fIcode\fP, |
| .ti +5n |
| .B const char *\fIsubject\fP, int *\fIovector\fP, |
| .ti +5n |
| .B int \fIstringcount\fP, const char *\fIstringname\fP, |
| .ti +5n |
| .B char *\fIbuffer\fP, int \fIbuffersize\fP); |
| .PP |
| .B int pcre_get_named_substring(const pcre *\fIcode\fP, |
| .ti +5n |
| .B const char *\fIsubject\fP, int *\fIovector\fP, |
| .ti +5n |
| .B int \fIstringcount\fP, const char *\fIstringname\fP, |
| .ti +5n |
| .B const char **\fIstringptr\fP); |
| .PP |
| 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 (PCRE_DUPNAMES was not set), you can find the number from the name by |
| calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled |
| pattern, and the second is the name. The yield of the function is the |
| subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) 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 |
| two functions that do the whole job. |
| .P |
| Most of the arguments of \fBpcre_copy_named_substring()\fP and |
| \fBpcre_get_named_substring()\fP are the same as those for the similarly named |
| functions that extract by number. As these are described in the previous |
| section, they are not re-described here. There are just two differences: |
| .P |
| First, instead of a substring number, a substring name is given. Second, there |
| is an extra argument, given at the start, which is a pointer to the compiled |
| pattern. This is needed in order to gain access to the name-to-number |
| translation table. |
| .P |
| These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they |
| then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as |
| appropriate. \fBNOTE:\fP If PCRE_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="pcrepattern.html#dupsubpatternnumber"> |
| .\" </a> |
| section on duplicate subpattern numbers |
| .\" |
| in the |
| .\" HREF |
| \fBpcrepattern\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 |
| .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, |
| .ti +5n |
| .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); |
| .PP |
| When a pattern is compiled with the PCRE_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 |
| \fBpcrepattern\fP |
| .\" |
| documentation. |
| .P |
| When duplicates are present, \fBpcre_copy_named_substring()\fP and |
| \fBpcre_get_named_substring()\fP return the first substring corresponding to |
| the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is |
| returned; no data is returned. The \fBpcre_get_stringnumber()\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 \fBpcre_get_stringtable_entries()\fP function. The first |
| argument is the compiled pattern, and the second is the name. The third and |
| fourth are pointers to variables which 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. The function itself returns the length of each entry, or |
| PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the 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, if any. |
| . |
| . |
| .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, consider |
| using the alternative matching function (see below) instead. If you cannot use |
| the alternative function, but still need to find all possible matches, you |
| can kludge it up by making use of the callout facility, which is described in |
| the |
| .\" HREF |
| \fBpcrecallout\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 \fBpcre_exec()\fP to backtrack and try |
| other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP |
| will yield PCRE_ERROR_NOMATCH. |
| . |
| . |
| .\" HTML <a name="dfamatch"></a> |
| .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION" |
| .rs |
| .sp |
| .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," |
| .ti +5n |
| .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, |
| .ti +5n |
| .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, |
| .ti +5n |
| .B int *\fIworkspace\fP, int \fIwscount\fP); |
| .P |
| The function \fBpcre_dfa_exec()\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 PCRE |
| 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 \fBpcre_dfa_exec()\fP does not support, see the |
| .\" HREF |
| \fBpcrematching\fP |
| .\" |
| documentation. |
| .P |
| The arguments for the \fBpcre_dfa_exec()\fP function are the same as for |
| \fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a |
| different way, and this is described below. The other common arguments are used |
| in the same way as for \fBpcre_exec()\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 will be needed for |
| patterns and subjects where there are a lot of potential matches. |
| .P |
| Here is an example of a simple call to \fBpcre_dfa_exec()\fP: |
| .sp |
| int rc; |
| int ovector[10]; |
| int wspace[20]; |
| rc = pcre_dfa_exec( |
| re, /* result of pcre_compile() */ |
| NULL, /* we didn't study the pattern */ |
| "some string", /* the subject string */ |
| 11, /* the length of the subject string */ |
| 0, /* start at offset 0 in the subject */ |
| 0, /* default options */ |
| ovector, /* vector of integers for substring information */ |
| 10, /* number of elements (NOT size in bytes) */ |
| wspace, /* working space vector */ |
| 20); /* number of elements (NOT size in bytes) */ |
| . |
| .SS "Option bits for \fBpcre_dfa_exec()\fP" |
| .rs |
| .sp |
| The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be |
| zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, |
| PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, |
| PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, |
| PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. |
| All but the last four of these are exactly the same as for \fBpcre_exec()\fP, |
| so their description is not repeated here. |
| .sp |
| PCRE_PARTIAL_HARD |
| PCRE_PARTIAL_SOFT |
| .sp |
| These have the same general effect as they do for \fBpcre_exec()\fP, but the |
| details are slightly different. When PCRE_PARTIAL_HARD is set for |
| \fBpcre_dfa_exec()\fP, it returns PCRE_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 also |
| been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH |
| is converted into PCRE_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 |
| \fBpcrepartial\fP |
| .\" |
| documentation. |
| .sp |
| PCRE_DFA_SHORTEST |
| .sp |
| Setting the PCRE_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 |
| PCRE_DFA_RESTART |
| .sp |
| When \fBpcre_dfa_exec()\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 PCRE_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 |
| \fBpcrepartial\fP |
| .\" |
| documentation. |
| . |
| . |
| .SS "Successful returns from \fBpcre_dfa_exec()\fP" |
| .rs |
| .sp |
| When \fBpcre_dfa_exec()\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 substrings themselves are returned in |
| \fIovector\fP. Each string uses two elements; the first is the offset to the |
| start, and the second is the offset to the end. In fact, all the strings have |
| the same start offset. (Space could have been saved by giving this only once, |
| but it was decided to retain some compatibility with the way \fBpcre_exec()\fP |
| returns data, even though the meaning of the strings is different.) |
| .P |
| The strings 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 |
| \fIovector\fP, the yield of the function is zero, and the vector is filled with |
| the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use |
| the entire \fIovector\fP for returning matched strings. |
| . |
| . |
| .SS "Error returns from \fBpcre_dfa_exec()\fP" |
| .rs |
| .sp |
| The \fBpcre_dfa_exec()\fP function returns a negative number when it fails. |
| Many of the errors are the same as for \fBpcre_exec()\fP, and these are |
| described |
| .\" HTML <a href="#errorlist"> |
| .\" </a> |
| above. |
| .\" |
| There are in addition the following errors that are specific to |
| \fBpcre_dfa_exec()\fP: |
| .sp |
| PCRE_ERROR_DFA_UITEM (-16) |
| .sp |
| This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern |
| that it does not support, for instance, the use of \eC or a back reference. |
| .sp |
| PCRE_ERROR_DFA_UCOND (-17) |
| .sp |
| This return is given if \fBpcre_dfa_exec()\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 |
| PCRE_ERROR_DFA_UMLIMIT (-18) |
| .sp |
| This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP |
| block that contains a setting of the \fImatch_limit\fP or |
| \fImatch_limit_recursion\fP fields. This is not supported (these fields are |
| meaningless for DFA matching). |
| .sp |
| PCRE_ERROR_DFA_WSSIZE (-19) |
| .sp |
| This return is given if \fBpcre_dfa_exec()\fP runs out of space in the |
| \fIworkspace\fP vector. |
| .sp |
| PCRE_ERROR_DFA_RECURSE (-20) |
| .sp |
| When a recursive subpattern is processed, the matching function calls itself |
| recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This |
| error is given if the output vector is not large enough. This should be |
| extremely rare, as a vector of size 1000 is used. |
| . |
| . |
| .SH "SEE ALSO" |
| .rs |
| .sp |
| \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3), |
| \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3), |
| \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3). |
| . |
| . |
| .SH AUTHOR |
| .rs |
| .sp |
| .nf |
| Philip Hazel |
| University Computing Service |
| Cambridge CB2 3QH, England. |
| .fi |
| . |
| . |
| .SH REVISION |
| .rs |
| .sp |
| .nf |
| Last updated: 02 December 2011 |
| Copyright (c) 1997-2011 University of Cambridge. |
| .fi |