Revision: 855
http://vcs.pcre.org/viewvc?view=rev&revision=855
Author: ph10
Date: 2012-01-06 15:08:49 +0000 (Fri, 06 Jan 2012)
Log Message:
-----------
Update for revised API.
Modified Paths:
--------------
code/trunk/doc/pcre16.3
Modified: code/trunk/doc/pcre16.3
===================================================================
--- code/trunk/doc/pcre16.3 2012-01-06 14:40:33 UTC (rev 854)
+++ code/trunk/doc/pcre16.3 2012-01-06 15:08:49 UTC (rev 855)
@@ -1,6 +1,139 @@
.TH PCRE 3
.SH NAME
PCRE - Perl-compatible regular expressions
+.SH "PCRE 16-BIT API BASIC FUNCTIONS"
+.rs
+.sp
+.B #include <pcre16.h>
+.PP
+.SM
+.B pcre16 *pcre16_compile(PCRE_SPTR16 \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 pcre16 *pcre16_compile2(PCRE_SPTR16 \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 pcre16_extra *pcre16_study(const pcre16 *\fIcode\fP, int \fIoptions\fP,
+.ti +5n
+.B const char **\fIerrptr\fP);
+.PP
+.B void pcre16_free_study(pcre16_extra *\fIextra\fP);
+.PP
+.B int pcre16_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
+.ti +5n
+.B "PCRE_SPTR16 \fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
+.ti +5n
+.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
+.
+.
+.SH "PCRE 16-BIT API AUXILIARY FUNCTIONS"
+.rs
+.sp
+.B pcre16_jit_stack *pcre16_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
+.PP
+.B void pcre16_jit_stack_free(pcre16_jit_stack *\fIstack\fP);
+.PP
+.B void pcre16_assign_jit_stack(pcre16_extra *\fIextra\fP,
+.ti +5n
+.B pcre16_jit_callback \fIcallback\fP, void *\fIdata\fP);
+.PP
+.B int pcre16_dfa_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
+.ti +5n
+.B "PCRE_SPTR16 \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 pcre16_copy_named_substring(const pcre16 *\fIcode\fP,
+.ti +5n
+.B PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
+.ti +5n
+.B int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP,
+.ti +5n
+.B PCRE_SCHAR16 *\fIbuffer\fP, int \fIbuffersize\fP);
+.PP
+.B int pcre16_copy_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
+.ti +5n
+.B int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_SCHAR16 *\fIbuffer\fP,
+.ti +5n
+.B int \fIbuffersize\fP);
+.PP
+.B int pcre16_get_named_substring(const pcre16 *\fIcode\fP,
+.ti +5n
+.B PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
+.ti +5n
+.B int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP,
+.ti +5n
+.B PCRE_SPTR16 *\fIstringptr\fP);
+.PP
+.B int pcre16_get_stringnumber(const pcre16 *\fIcode\fP,
+.ti +5n
+.B PCRE_SPTR16 \fIname\fP);
+.PP
+.B int pcre16_get_stringtable_entries(const pcre16 *\fIcode\fP,
+.ti +5n
+.B PCRE_SPTR16 \fIname\fP, PCRE_SCHAR16 **\fIfirst\fP, PCRE_SCHAR16 **\fIlast\fP);
+.PP
+.B int pcre16_get_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
+.ti +5n
+.B int \fIstringcount\fP, int \fIstringnumber\fP,
+.ti +5n
+.B PCRE_SPTR16 *\fIstringptr\fP);
+.PP
+.B int pcre16_get_substring_list(PCRE_SPTR16 \fIsubject\fP,
+.ti +5n
+.B int *\fIovector\fP, int \fIstringcount\fP, "PCRE_SPTR16 **\fIlistptr\fP);"
+.PP
+.B void pcre16_free_substring(PCRE_SPTR16 \fIstringptr\fP);
+.PP
+.B void pcre16_free_substring_list(PCRE_SPTR16 *\fIstringptr\fP);
+.PP
+.B const unsigned char *pcre16_maketables(void);
+.PP
+.B int pcre16_fullinfo(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
+.ti +5n
+.B int \fIwhat\fP, void *\fIwhere\fP);
+.PP
+.B int pcre16_refcount(pcre16 *\fIcode\fP, int \fIadjust\fP);
+.PP
+.B int pcre16_config(int \fIwhat\fP, void *\fIwhere\fP);
+.PP
+.B const char *pcre16_version(void);
+.
+.
+.SH "PCRE 16-BIT API INDIRECTED FUNCTIONS"
+.rs
+.sp
+.B void *(*pcre16_malloc)(size_t);
+.PP
+.B void (*pcre16_free)(void *);
+.PP
+.B void *(*pcre16_stack_malloc)(size_t);
+.PP
+.B void (*pcre16_stack_free)(void *);
+.PP
+.B int (*pcre16_callout)(pcre16_callout_block *);
+.
+.
+.SH "PCRE 16-BIT API 16-BIT-ONLY FUNCTION"
+.rs
+.sp
+.B int pcre16_utf16_to_host_byte_order(PCRE_SCHAR16 *\fIoutput\fP,
+.ti +5n
+.B PCRE_SPTR16 \fIinput\fP, int \fIlength\fP, int *\fIbyte_order\fP,
+.ti +5n
+.B int \fIkeep_boms\fP);
+.
+.
.SH "THE PCRE 16-BIT LIBRARY"
.rs
.sp
@@ -9,10 +142,10 @@
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 string arguments are different. To avoid
+the data types of their arguments and results are different. To avoid
over-complication and reduce the documentation maintenance load, most of the
-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
+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
@@ -27,9 +160,18 @@
.rs
.sp
There is only one header file, \fBpcre.h\fP. It contains prototypes for all the
-functions in both libraries, as well as definitions of flags, error codes, etc.
+functions in both 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
@@ -43,53 +185,47 @@
maintainer to modify the definition appropriately.
.
.
-.SH "16-BIT FUNCTIONS WITH DIFFERING ARGUMENT TYPES"
+.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. All of these functions have the same number of arguments, and
-yield the same results. Many of them also have exactly the same argument types.
-Those that differ are as follows:
-
-\fBpcre16_compile()\fP and \fBpcre16_compile2()\fP: the type of the first
-argument must be PCRE_SPTR16 instead of "const char *".
-
-\fBpcre16_exec()\fP and \fBpcre16_dfa_exec()\fP: the type of the third argument
-must be PCRE_SPTR16 instead of "const char *".
-
-\fBpcre16_copy_named_substring()\fP: the type of the second and fifth agruments
-must be PCRE_SPTR16 instead of "const char *" and the type of the sixth
-argument must be "PCRE_SCHAR16 *" instead of "char *".
-
-\fBpcre16_copy_substring()\fP: the type of the first argument must be
-PCRE_SPTR16 instead of "const char *" and the type of the fifth argument must
-be "PCRE_SCHAR16 *" instead of "char *".
-
-\fBpcre16_get_named_substring()\fP: the type of the second and fifth agruments
-must be PCRE_SPTR16 instead of "const char *" and the type of the sixth
-argument must be "PCRE_SPTR16 *" instead of "const char **".
-
-\fBpcre16_get_substring()\fP: the type of the first argument must be
-PCRE_SPTR16 instead of "const char *" and the type of the fifth argument must
-be "PCRE_SPTR16 *" intead of "const char **".
-
-\fBpcre16_free_substring()\fP: the type of the argument must be PCRE_SPTR16
-instead of "const char *".
-
-\fBpcre16_get_substring_list()\fP: the type of the first argument must be
-PCRE_SPTR16 intead of "const char *", and the type of the fourth argument must
-be "PCRE_SPTR16 **" intead of "const char ***".
-
-\fBpcre16_free_substring_list()\fP: the type of the argument must be
-"PCRE_SPTR16 *" instead of "const char **".
-
-\fBpcre16_get_stringnumber()\fP: the type of the second argument must be
-PCRE_SPTR16 instead of "const char *".
-
-\fBpcre16_get_stringtable_entries()\fP: the types of the second, third, and
-fourth arguments must be PCRE_SPTR16, "PCRE_SCHAR16 **", and "PCRE_SCHAR16 **"
-intead of "const char *", "char **", and "char **".
+\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 \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 non 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"
@@ -105,7 +241,7 @@
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
-items.
+units.
.
.
.SH "OPTION NAMES"
@@ -126,24 +262,20 @@
.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
+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.
+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 BOM at its
-start. The PCRE functions do not handle this. However a function called
-\fBpcre16_utf16_to_host_byte_order()\fP is provided. It checks the byte order
-of a UTF-16 string and converts it if necessary, optionally removing the BOM
-data. It is documented with all the other functions in the
-.\" HREF
-\fBpcreapi\fP
-.\"
-page.
+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"
@@ -156,12 +288,22 @@
\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.
-They are documented in the
+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.
+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 Invalid character 0xfffe
.
.
.SH "ERROR TEXTS"
@@ -217,6 +359,6 @@
.rs
.sp
.nf
-Last updated: 03 January 2012
+Last updated: 06 January 2012
Copyright (c) 1997-2012 University of Cambridge.
.fi
