| .TH PCRE 3 "12 May 2013" "PCRE 8.33" |
| .SH NAME |
| PCRE - Perl-compatible regular expressions |
| .sp |
| .B #include <pcre.h> |
| . |
| . |
| .SH "PCRE 16-BIT API BASIC FUNCTIONS" |
| .rs |
| .sp |
| .nf |
| .B pcre16 *pcre16_compile(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP, |
| .B " const char **\fIerrptr\fP, int *\fIerroffset\fP," |
| .B " const unsigned char *\fItableptr\fP);" |
| .sp |
| .B pcre16 *pcre16_compile2(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP, |
| .B " int *\fIerrorcodeptr\fP," |
| .B " const char **\fIerrptr\fP, int *\fIerroffset\fP," |
| .B " const unsigned char *\fItableptr\fP);" |
| .sp |
| .B pcre16_extra *pcre16_study(const pcre16 *\fIcode\fP, int \fIoptions\fP, |
| .B " const char **\fIerrptr\fP);" |
| .sp |
| .B void pcre16_free_study(pcre16_extra *\fIextra\fP); |
| .sp |
| .B int pcre16_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," |
| .B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," |
| .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);" |
| .sp |
| .B int pcre16_dfa_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," |
| .B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP," |
| .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP," |
| .B " int *\fIworkspace\fP, int \fIwscount\fP);" |
| .fi |
| . |
| . |
| .SH "PCRE 16-BIT API STRING EXTRACTION FUNCTIONS" |
| .rs |
| .sp |
| .nf |
| .B int pcre16_copy_named_substring(const pcre16 *\fIcode\fP, |
| .B " PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP," |
| .B " int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP," |
| .B " PCRE_UCHAR16 *\fIbuffer\fP, int \fIbuffersize\fP);" |
| .sp |
| .B int pcre16_copy_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP, |
| .B " int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_UCHAR16 *\fIbuffer\fP," |
| .B " int \fIbuffersize\fP);" |
| .sp |
| .B int pcre16_get_named_substring(const pcre16 *\fIcode\fP, |
| .B " PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP," |
| .B " int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP," |
| .B " PCRE_SPTR16 *\fIstringptr\fP);" |
| .sp |
| .B int pcre16_get_stringnumber(const pcre16 *\fIcode\fP, |
| .B " PCRE_SPTR16 \fIname\fP); |
| .sp |
| .B int pcre16_get_stringtable_entries(const pcre16 *\fIcode\fP, |
| .B " PCRE_SPTR16 \fIname\fP, PCRE_UCHAR16 **\fIfirst\fP, PCRE_UCHAR16 **\fIlast\fP);" |
| .sp |
| .B int pcre16_get_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP, |
| .B " int \fIstringcount\fP, int \fIstringnumber\fP," |
| .B " PCRE_SPTR16 *\fIstringptr\fP);" |
| .sp |
| .B int pcre16_get_substring_list(PCRE_SPTR16 \fIsubject\fP, |
| .B " int *\fIovector\fP, int \fIstringcount\fP, PCRE_SPTR16 **\fIlistptr\fP);" |
| .sp |
| .B void pcre16_free_substring(PCRE_SPTR16 \fIstringptr\fP); |
| .sp |
| .B void pcre16_free_substring_list(PCRE_SPTR16 *\fIstringptr\fP); |
| .fi |
| . |
| . |
| .SH "PCRE 16-BIT API AUXILIARY FUNCTIONS" |
| .rs |
| .sp |
| .nf |
| .B pcre16_jit_stack *pcre16_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP); |
| .sp |
| .B void pcre16_jit_stack_free(pcre16_jit_stack *\fIstack\fP); |
| .sp |
| .B void pcre16_assign_jit_stack(pcre16_extra *\fIextra\fP, |
| .B " pcre16_jit_callback \fIcallback\fP, void *\fIdata\fP);" |
| .sp |
| .B const unsigned char *pcre16_maketables(void); |
| .sp |
| .B int pcre16_fullinfo(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP," |
| .B " int \fIwhat\fP, void *\fIwhere\fP);" |
| .sp |
| .B int pcre16_refcount(pcre16 *\fIcode\fP, int \fIadjust\fP); |
| .sp |
| .B int pcre16_config(int \fIwhat\fP, void *\fIwhere\fP); |
| .sp |
| .B const char *pcre16_version(void); |
| .sp |
| .B int pcre16_pattern_to_host_byte_order(pcre16 *\fIcode\fP, |
| .B " pcre16_extra *\fIextra\fP, const unsigned char *\fItables\fP);" |
| .fi |
| . |
| . |
| .SH "PCRE 16-BIT API INDIRECTED FUNCTIONS" |
| .rs |
| .sp |
| .nf |
| .B void *(*pcre16_malloc)(size_t); |
| .sp |
| .B void (*pcre16_free)(void *); |
| .sp |
| .B void *(*pcre16_stack_malloc)(size_t); |
| .sp |
| .B void (*pcre16_stack_free)(void *); |
| .sp |
| .B int (*pcre16_callout)(pcre16_callout_block *); |
| .fi |
| . |
| . |
| .SH "PCRE 16-BIT API 16-BIT-ONLY FUNCTION" |
| .rs |
| .sp |
| .nf |
| .B int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *\fIoutput\fP, |
| .B " PCRE_SPTR16 \fIinput\fP, int \fIlength\fP, int *\fIbyte_order\fP," |
| .B " int \fIkeep_boms\fP);" |
| .fi |
| . |
| . |
| .SH "THE PCRE 16-BIT LIBRARY" |
| .rs |
| .sp |
| Starting with release 8.30, it is possible to compile a PCRE library that |
| supports 16-bit character strings, including UTF-16 strings, as well as or |
| instead of the original 8-bit library. The majority of the work to make this |
| possible was done by Zoltan Herczeg. The two libraries contain identical sets |
| of functions, used in exactly the same way. Only the names of the functions and |
| the data types of their arguments and results are different. To avoid |
| over-complication and reduce the documentation maintenance load, most of the |
| PCRE documentation describes the 8-bit library, with only occasional references |
| to the 16-bit library. This page describes what is different when you use the |
| 16-bit library. |
| .P |
| WARNING: A single application can be linked with both libraries, but you must |
| take care when processing any particular pattern to use functions from just one |
| library. For example, if you want to study a pattern that was compiled with |
| \fBpcre16_compile()\fP, you must do so with \fBpcre16_study()\fP, not |
| \fBpcre_study()\fP, and you must free the study data with |
| \fBpcre16_free_study()\fP. |
| . |
| . |
| .SH "THE HEADER FILE" |
| .rs |
| .sp |
| There is only one header file, \fBpcre.h\fP. It contains prototypes for all the |
| functions in all libraries, as well as definitions of flags, structures, error |
| codes, etc. |
| . |
| . |
| .SH "THE LIBRARY NAME" |
| .rs |
| .sp |
| In Unix-like systems, the 16-bit library is called \fBlibpcre16\fP, and can |
| normally be accesss by adding \fB-lpcre16\fP to the command for linking an |
| application that uses PCRE. |
| . |
| . |
| .SH "STRING TYPES" |
| .rs |
| .sp |
| In the 8-bit library, strings are passed to PCRE library functions as vectors |
| of bytes with the C type "char *". In the 16-bit library, strings are passed as |
| vectors of unsigned 16-bit quantities. The macro PCRE_UCHAR16 specifies an |
| appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In |
| very many environments, "short int" is a 16-bit data type. When PCRE is built, |
| it defines PCRE_UCHAR16 as "unsigned short int", but checks that it really is a |
| 16-bit data type. If it is not, the build fails with an error message telling |
| the maintainer to modify the definition appropriately. |
| . |
| . |
| .SH "STRUCTURE TYPES" |
| .rs |
| .sp |
| The types of the opaque structures that are used for compiled 16-bit patterns |
| and JIT stacks are \fBpcre16\fP and \fBpcre16_jit_stack\fP respectively. The |
| type of the user-accessible structure that is returned by \fBpcre16_study()\fP |
| is \fBpcre16_extra\fP, and the type of the structure that is used for passing |
| data to a callout function is \fBpcre16_callout_block\fP. These structures |
| contain the same fields, with the same names, as their 8-bit counterparts. The |
| only difference is that pointers to character strings are 16-bit instead of |
| 8-bit types. |
| . |
| . |
| .SH "16-BIT FUNCTIONS" |
| .rs |
| .sp |
| For every function in the 8-bit library there is a corresponding function in |
| the 16-bit library with a name that starts with \fBpcre16_\fP instead of |
| \fBpcre_\fP. The prototypes are listed above. In addition, there is one extra |
| function, \fBpcre16_utf16_to_host_byte_order()\fP. This is a utility function |
| that converts a UTF-16 character string to host byte order if necessary. The |
| other 16-bit functions expect the strings they are passed to be in host byte |
| order. |
| .P |
| The \fIinput\fP and \fIoutput\fP arguments of |
| \fBpcre16_utf16_to_host_byte_order()\fP may point to the same address, that is, |
| conversion in place is supported. The output buffer must be at least as long as |
| the input. |
| .P |
| The \fIlength\fP argument specifies the number of 16-bit data units in the |
| input string; a negative value specifies a zero-terminated string. |
| .P |
| If \fIbyte_order\fP is NULL, it is assumed that the string starts off in host |
| byte order. This may be changed by byte-order marks (BOMs) anywhere in the |
| string (commonly as the first character). |
| .P |
| If \fIbyte_order\fP is not NULL, a non-zero value of the integer to which it |
| points means that the input starts off in host byte order, otherwise the |
| opposite order is assumed. Again, BOMs in the string can change this. The final |
| byte order is passed back at the end of processing. |
| .P |
| If \fIkeep_boms\fP is not zero, byte-order mark characters (0xfeff) are copied |
| into the output string. Otherwise they are discarded. |
| .P |
| The result of the function is the number of 16-bit units placed into the output |
| buffer, including the zero terminator if the string was zero-terminated. |
| . |
| . |
| .SH "SUBJECT STRING OFFSETS" |
| .rs |
| .sp |
| The lengths and starting offsets of subject strings must be specified in 16-bit |
| data units, and the offsets within subject strings that are returned by the |
| matching functions are in also 16-bit units rather than bytes. |
| . |
| . |
| .SH "NAMED SUBPATTERNS" |
| .rs |
| .sp |
| The name-to-number translation table that is maintained for named subpatterns |
| uses 16-bit characters. The \fBpcre16_get_stringtable_entries()\fP function |
| returns the length of each entry in the table as the number of 16-bit data |
| units. |
| . |
| . |
| .SH "OPTION NAMES" |
| .rs |
| .sp |
| There are two new general option names, PCRE_UTF16 and PCRE_NO_UTF16_CHECK, |
| which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In |
| fact, these new options define the same bits in the options word. There is a |
| discussion about the |
| .\" HTML <a href="pcreunicode.html#utf16strings"> |
| .\" </a> |
| validity of UTF-16 strings |
| .\" |
| in the |
| .\" HREF |
| \fBpcreunicode\fP |
| .\" |
| page. |
| .P |
| For the \fBpcre16_config()\fP function there is an option PCRE_CONFIG_UTF16 |
| that returns 1 if UTF-16 support is configured, otherwise 0. If this option is |
| given to \fBpcre_config()\fP or \fBpcre32_config()\fP, or if the |
| PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to \fBpcre16_config()\fP, |
| the result is the PCRE_ERROR_BADOPTION error. |
| . |
| . |
| .SH "CHARACTER CODES" |
| .rs |
| .sp |
| In 16-bit mode, when PCRE_UTF16 is not set, character values are treated in the |
| same way as in 8-bit, non UTF-8 mode, except, of course, that they can range |
| from 0 to 0xffff instead of 0 to 0xff. Character types for characters less than |
| 0xff can therefore be influenced by the locale in the same way as before. |
| Characters greater than 0xff have only one case, and no "type" (such as letter |
| or digit). |
| .P |
| In UTF-16 mode, the character code is Unicode, in the range 0 to 0x10ffff, with |
| the exception of values in the range 0xd800 to 0xdfff because those are |
| "surrogate" values that are used in pairs to encode values greater than 0xffff. |
| .P |
| A UTF-16 string can indicate its endianness by special code knows as a |
| byte-order mark (BOM). The PCRE functions do not handle this, expecting strings |
| to be in host byte order. A utility function called |
| \fBpcre16_utf16_to_host_byte_order()\fP is provided to help with this (see |
| above). |
| . |
| . |
| .SH "ERROR NAMES" |
| .rs |
| .sp |
| The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 correspond to |
| their 8-bit counterparts. The error PCRE_ERROR_BADMODE is given when a compiled |
| pattern is passed to a function that processes patterns in the other |
| mode, for example, if a pattern compiled with \fBpcre_compile()\fP is passed to |
| \fBpcre16_exec()\fP. |
| .P |
| There are new error codes whose names begin with PCRE_UTF16_ERR for invalid |
| UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that |
| are described in the section entitled |
| .\" HTML <a href="pcreapi.html#badutf8reasons"> |
| .\" </a> |
| "Reason codes for invalid UTF-8 strings" |
| .\" |
| in the main |
| .\" HREF |
| \fBpcreapi\fP |
| .\" |
| page. The UTF-16 errors are: |
| .sp |
| PCRE_UTF16_ERR1 Missing low surrogate at end of string |
| PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate |
| PCRE_UTF16_ERR3 Isolated low surrogate |
| PCRE_UTF16_ERR4 Non-character |
| . |
| . |
| .SH "ERROR TEXTS" |
| .rs |
| .sp |
| If there is an error while compiling a pattern, the error text that is passed |
| back by \fBpcre16_compile()\fP or \fBpcre16_compile2()\fP is still an 8-bit |
| character string, zero-terminated. |
| . |
| . |
| .SH "CALLOUTS" |
| .rs |
| .sp |
| The \fIsubject\fP and \fImark\fP fields in the callout block that is passed to |
| a callout function point to 16-bit vectors. |
| . |
| . |
| .SH "TESTING" |
| .rs |
| .sp |
| The \fBpcretest\fP program continues to operate with 8-bit input and output |
| files, but it can be used for testing the 16-bit library. If it is run with the |
| command line option \fB-16\fP, patterns and subject strings are converted from |
| 8-bit to 16-bit before being passed to PCRE, and the 16-bit library functions |
| are used instead of the 8-bit ones. Returned 16-bit strings are converted to |
| 8-bit for output. If both the 8-bit and the 32-bit libraries were not compiled, |
| \fBpcretest\fP defaults to 16-bit and the \fB-16\fP option is ignored. |
| .P |
| When PCRE is being built, the \fBRunTest\fP script that is called by "make |
| check" uses the \fBpcretest\fP \fB-C\fP option to discover which of the 8-bit, |
| 16-bit and 32-bit libraries has been built, and runs the tests appropriately. |
| . |
| . |
| .SH "NOT SUPPORTED IN 16-BIT MODE" |
| .rs |
| .sp |
| Not all the features of the 8-bit library are available with the 16-bit |
| library. The C++ and POSIX wrapper functions support only the 8-bit library, |
| and the \fBpcregrep\fP program is at present 8-bit only. |
| . |
| . |
| .SH AUTHOR |
| .rs |
| .sp |
| .nf |
| Philip Hazel |
| University Computing Service |
| Cambridge CB2 3QH, England. |
| .fi |
| . |
| . |
| .SH REVISION |
| .rs |
| .sp |
| .nf |
| Last updated: 12 May 2013 |
| Copyright (c) 1997-2013 University of Cambridge. |
| .fi |