Timerix/utf8proc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rm ruby and pgsql plugins: keep libutf8proc repo focused exclusively on the C library

Browse Source
This commit is contained in:
Steven G. Johnson 2014-07-15 15:32:53 -04:00
parent ab9520d188
commit c0f2b512a0
9 changed files with 0 additions and 544 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
README
View File

@ -45,59 +45,6 @@ The documentation for the C library is found in the utf8proc.h header file.
strings, unless you want to allocate memory yourself. strings, unless you want to allocate memory yourself.
*** RUBY API ***
The ruby library adds the methods "utf8map" and "utf8map!" to the String
class, and the method "utf8" to the Integer class.
The String#utf8map method does the same as the "utf8proc_map" C function.
Options for the mapping procedure are passed as symbols, i.e:
"Hello".utf8map(:casefold) => "hello"
The descriptions of all options are found in the C header file
"utf8proc.h". Please notice that the according symbols in ruby are all
lowercase.
String#utf8map! is the destructive function in the meaning that the string
is replaced by the result.
There are shortcuts for the 4 normalization forms specified by Unicode:
String#utf8nfd, String#utf8nfd!,
String#utf8nfc, String#utf8nfc!,
String#utf8nfkd, String#utf8nfkd!,
String#utf8nfkc, String#utf8nfkc!
The method Integer#utf8 returns a UTF-8 string, which is containing the
unicode char given by the code point.
0x000A.utf8 => "\n"
0x2028.utf8 => "\342\200\250"
*** POSTGRESQL API ***
For PostgreSQL there are two SQL functions supplied named "unifold" and
"unistrip". These functions function can be used to prepare index fields in
order to be folded in a way where string-comparisons make more sense, e.g.
where "bathtub" == "bath<soft hyphen>tub"
or "Hello World" == "hello world".
CREATE TABLE people (
id serial8 primary key,
name text,
CHECK (unifold(name) NOTNULL)
);
CREATE INDEX name_idx ON people (unifold(name));
SELECT * FROM people WHERE unifold(name) = unifold('John Doe');
The function "unistrip" removes character marks like accents or diaeresis,
while "unifold" keeps then.
NOTICE: The outputs of the function can change between releases, as
utf8proc does not follow a versioning stability policy. You have to
rebuild your database indicies, if you upgrade to a newer version
of utf8proc.
*** TODO *** *** TODO ***
- detect stable code points and process segments independently in order to - detect stable code points and process segments independently in order to

10
pgsql/Makefile
View File

@ -1,10 +0,0 @@
utf8proc_pgsql.so: utf8proc_pgsql.o
ld -shared -o utf8proc_pgsql.so utf8proc_pgsql.o
utf8proc_pgsql.o: utf8proc_pgsql.c
gcc -Wall -fpic -c -I`pg_config --includedir-server` \
-o utf8proc_pgsql.o utf8proc_pgsql.c
clean:
rm -f *.o *.so

6
pgsql/utf8proc.sql
View File

@ -1,6 +0,0 @@
CREATE OR REPLACE FUNCTION unifold (text) RETURNS text
LANGUAGE 'c' IMMUTABLE STRICT AS '$libdir/utf8proc_pgsql.so',
'utf8proc_pgsql_unifold';
CREATE OR REPLACE FUNCTION unistrip (text) RETURNS text
LANGUAGE 'c' IMMUTABLE STRICT AS '$libdir/utf8proc_pgsql.so',
'utf8proc_pgsql_unistrip';

139
pgsql/utf8proc_pgsql.c
View File

@ -1,139 +0,0 @@
/*
* Copyright (c) Public Software Group e. V., Berlin, Germany
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
/*
* File name: pgsql/utf8proc_pgsql.c
*
* Description:
* PostgreSQL extension to provide two functions 'unifold' and 'unistrip',
* which can be used to case-fold and normalize index fields and
* optionally strip marks (e.g. accents) from strings.
*/
#include "../utf8proc.c"
#include <postgres.h>
#include <utils/elog.h>
#include <fmgr.h>
#include <string.h>
#include <unistd.h>
#include <utils/builtins.h>
#ifdef PG_MODULE_MAGIC
PG_MODULE_MAGIC;
#endif
#define UTF8PROC_PGSQL_FOLD_OPTS ( UTF8PROC_REJECTNA | UTF8PROC_COMPAT | \
UTF8PROC_COMPOSE | UTF8PROC_STABLE | UTF8PROC_IGNORE | UTF8PROC_STRIPCC | \
UTF8PROC_NLF2LF | UTF8PROC_CASEFOLD | UTF8PROC_LUMP )
#define UTF8PROC_PGSQL_STRIP_OPTS ( UTF8PROC_REJECTNA | UTF8PROC_COMPAT | \
UTF8PROC_COMPOSE | UTF8PROC_STABLE | UTF8PROC_IGNORE | UTF8PROC_STRIPCC | \
UTF8PROC_NLF2LF | UTF8PROC_CASEFOLD | UTF8PROC_LUMP | UTF8PROC_STRIPMARK )
ssize_t utf8proc_pgsql_utf8map(
text *input_string, text **output_string_ptr, int options
) {
ssize_t result;
text *output_string;
result = utf8proc_decompose(
VARDATA(input_string), VARSIZE(input_string) - VARHDRSZ,
NULL, 0, options
);
if (result < 0) return result;
if (result > (SIZE_MAX-1-VARHDRSZ)/sizeof(int32_t))
return UTF8PROC_ERROR_OVERFLOW;
/* reserve one extra byte for termination */
*output_string_ptr = palloc(result * sizeof(int32_t) + 1 + VARHDRSZ);
output_string = *output_string_ptr;
if (!output_string) return UTF8PROC_ERROR_NOMEM;
result = utf8proc_decompose(
VARDATA(input_string), VARSIZE(input_string) - VARHDRSZ,
(int32_t *)VARDATA(output_string), result, options
);
if (result < 0) return result;
result = utf8proc_reencode(
(int32_t *)VARDATA(output_string), result, options
);
if (result >= 0) SET_VARSIZE(output_string, result + VARHDRSZ);
return result;
}
void utf8proc_pgsql_utf8map_errchk(ssize_t result, text *output_string) {
if (result < 0) {
int sqlerrcode;
if (output_string) pfree(output_string);
switch(result) {
case UTF8PROC_ERROR_NOMEM:
sqlerrcode = ERRCODE_OUT_OF_MEMORY; break;
case UTF8PROC_ERROR_OVERFLOW:
sqlerrcode = ERRCODE_PROGRAM_LIMIT_EXCEEDED; break;
case UTF8PROC_ERROR_INVALIDUTF8:
case UTF8PROC_ERROR_NOTASSIGNED:
return;
default:
sqlerrcode = ERRCODE_INTERNAL_ERROR;
}
ereport(ERROR, (
errcode(sqlerrcode),
errmsg("%s", utf8proc_errmsg(result))
));
}
}
PG_FUNCTION_INFO_V1(utf8proc_pgsql_unifold);
Datum utf8proc_pgsql_unifold(PG_FUNCTION_ARGS) {
text *input_string;
text *output_string = NULL;
ssize_t result;
input_string = PG_GETARG_TEXT_P(0);
result = utf8proc_pgsql_utf8map(
input_string, &output_string, UTF8PROC_PGSQL_FOLD_OPTS
);
PG_FREE_IF_COPY(input_string, 0);
utf8proc_pgsql_utf8map_errchk(result, output_string);
if (result >= 0) {
PG_RETURN_TEXT_P(output_string);
} else {
PG_RETURN_NULL();
}
}
PG_FUNCTION_INFO_V1(utf8proc_pgsql_unistrip);
Datum utf8proc_pgsql_unistrip(PG_FUNCTION_ARGS) {
text *input_string;
text *output_string = NULL;
ssize_t result;
input_string = PG_GETARG_TEXT_P(0);
result = utf8proc_pgsql_utf8map(
input_string, &output_string, UTF8PROC_PGSQL_STRIP_OPTS
);
PG_FREE_IF_COPY(input_string, 0);
utf8proc_pgsql_utf8map_errchk(result, output_string);
if (result >= 0) {
PG_RETURN_TEXT_P(output_string);
} else {
PG_RETURN_NULL();
}
}

2
ruby/extconf.rb
View File

@ -1,2 +0,0 @@
require 'mkmf'
create_makefile("utf8proc_native")

64
ruby/gem/LICENSE
View File

@ -1,64 +0,0 @@
Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
Permission is hereby granted, free of charge, to any person obtaining a
copy of this software and associated documentation files (the "Software"),
to deal in the Software without restriction, including without limitation
the rights to use, copy, modify, merge, publish, distribute, sublicense,
and/or sell copies of the Software, and to permit persons to whom the
Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
This software distribution contains derived data from a modified version of
the Unicode data files. The following license applies to that data:
COPYRIGHT AND PERMISSION NOTICE
Copyright (c) 1991-2007 Unicode, Inc. All rights reserved. Distributed
under the Terms of Use in http://www.unicode.org/copyright.html.
Permission is hereby granted, free of charge, to any person obtaining a
copy of the Unicode data files and any associated documentation (the "Data
Files") or Unicode software and any associated documentation (the
"Software") to deal in the Data Files or Software without restriction,
including without limitation the rights to use, copy, modify, merge,
publish, distribute, and/or sell copies of the Data Files or Software, and
to permit persons to whom the Data Files or Software are furnished to do
so, provided that (a) the above copyright notice(s) and this permission
notice appear with all copies of the Data Files or Software, (b) both the
above copyright notice(s) and this permission notice appear in associated
documentation, and (c) there is clear notice in each modified Data File or
in the Software as well as in the documentation associated with the Data
File(s) or Software that the data or software has been modified.
THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF
THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS
INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR
CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF
USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THE DATA FILES OR SOFTWARE.
Except as contained in this notice, the name of a copyright holder shall
not be used in advertising or otherwise to promote the sale, use or other
dealings in these Data Files or Software without prior written
authorization of the copyright holder.
Unicode and the Unicode logo are trademarks of Unicode, Inc., and may be
registered in some jurisdictions. All other trademarks and registered
trademarks mentioned herein are the property of their respective owners.

12
ruby/gem/utf8proc.gemspec
View File

@ -1,12 +0,0 @@
require 'rubygems'
SPEC = Gem::Specification.new do |s|
s.name = 'utf8proc'
s.version = '1.1.6'
s.author = 'Public Software Group e. V., Berlin, Germany'
s.homepage = 'http://www.public-software-group.org/utf8proc'
s.summary = 'UTF-8 Unicode string processing'
s.files = ['LICENSE', 'lib/utf8proc.rb', 'ext/utf8proc_native.c']
s.require_path = 'lib/'
s.extensions = ['ext/extconf.rb']
s.has_rdoc = false
end

98
ruby/utf8proc.rb
View File

@ -1,98 +0,0 @@
# Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
#
# File name: ruby/utf8proc.rb
#
# Description:
# Part of the ruby wrapper for libutf8proc, which is written in ruby.
#
require 'utf8proc_native'
module Utf8Proc
SpecialChars = {
:HT => "\x09",
:LF => "\x0A",
:VT => "\x0B",
:FF => "\x0C",
:CR => "\x0D",
:FS => "\x1C",
:GS => "\x1D",
:RS => "\x1E",
:US => "\x1F",
:LS => "\xE2\x80\xA8",
:PS => "\xE2\x80\xA9",
}
module StringExtensions
def utf8map(*option_array)
options = 0
option_array.each do |option|
flag = Utf8Proc::Options[option]
raise ArgumentError, "Unknown argument given to String#utf8map." unless
flag
options |= flag
end
return Utf8Proc::utf8map(self, options)
end
def utf8map!(*option_array)
self.replace(self.utf8map(*option_array))
end
def utf8nfd; utf8map( :stable, :decompose); end
def utf8nfd!; utf8map!(:stable, :decompose); end
def utf8nfc; utf8map( :stable, :compose); end
def utf8nfc!; utf8map!(:stable, :compose); end
def utf8nfkd; utf8map( :stable, :decompose, :compat); end
def utf8nfkd!; utf8map!(:stable, :decompose, :compat); end
def utf8nfkc; utf8map( :stable, :compose, :compat); end
def utf8nfkc!; utf8map!(:stable, :compose, :compat); end
def utf8chars
result = self.utf8map(:charbound).split("\377")
result.shift if result.first == ""
result
end
def char_ary
# depecated, use String#utf8chars instead
utf8chars
end
end
module IntegerExtensions
def utf8
return Utf8Proc::utf8char(self)
end
end
end
class String
include(Utf8Proc::StringExtensions)
end
class Integer
include(Utf8Proc::IntegerExtensions)
end

160
ruby/utf8proc_native.c
View File

@ -1,160 +0,0 @@
/*
* Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
/*
* File name: ruby/utf8proc_native.c
*
* Description:
* Native part of the ruby wrapper for libutf8proc.
*/
#include "../utf8proc.c"
#include "ruby.h"
#ifndef RSTRING_PTR
#define RSTRING_PTR(s) (RSTRING(s)->ptr)
#endif
#ifndef RSTRING_LEN
#define RSTRING_LEN(s) (RSTRING(s)->len)
#endif
typedef struct utf8proc_ruby_mapenv_struct {
int32_t *buffer;
} utf8proc_ruby_mapenv_t;
void utf8proc_ruby_mapenv_free(utf8proc_ruby_mapenv_t *env) {
free(env->buffer);
free(env);
}
VALUE utf8proc_ruby_module;
VALUE utf8proc_ruby_options;
VALUE utf8proc_ruby_eUnicodeError;
VALUE utf8proc_ruby_eInvalidUtf8Error;
VALUE utf8proc_ruby_eCodeNotAssignedError;
VALUE utf8proc_ruby_map_error(ssize_t result) {
VALUE excpt_class;
switch (result) {
case UTF8PROC_ERROR_NOMEM:
excpt_class = rb_eNoMemError; break;
case UTF8PROC_ERROR_OVERFLOW:
case UTF8PROC_ERROR_INVALIDOPTS:
excpt_class = rb_eArgError; break;
case UTF8PROC_ERROR_INVALIDUTF8:
excpt_class = utf8proc_ruby_eInvalidUtf8Error; break;
case UTF8PROC_ERROR_NOTASSIGNED:
excpt_class = utf8proc_ruby_eCodeNotAssignedError; break;
default:
excpt_class = rb_eRuntimeError;
}
rb_raise(excpt_class, "%s", utf8proc_errmsg(result));
return Qnil;
}
VALUE utf8proc_ruby_map(VALUE self, VALUE str_param, VALUE options_param) {
VALUE str;
int options;
VALUE env_obj;
utf8proc_ruby_mapenv_t *env;
ssize_t result;
VALUE retval;
str = StringValue(str_param);
options = NUM2INT(options_param) & ~UTF8PROC_NULLTERM;
env_obj = Data_Make_Struct(rb_cObject, utf8proc_ruby_mapenv_t, NULL,
utf8proc_ruby_mapenv_free, env);
result = utf8proc_decompose(RSTRING_PTR(str), RSTRING_LEN(str),
NULL, 0, options);
if (result < 0) {
utf8proc_ruby_map_error(result);
return Qnil; /* needed to prevent problems with optimization */
}
env->buffer = ALLOC_N(int32_t, result+1);
result = utf8proc_decompose(RSTRING_PTR(str), RSTRING_LEN(str),
env->buffer, result, options);
if (result < 0) {
free(env->buffer);
env->buffer = 0;
utf8proc_ruby_map_error(result);
return Qnil; /* needed to prevent problems with optimization */
}
result = utf8proc_reencode(env->buffer, result, options);
if (result < 0) {
free(env->buffer);
env->buffer = 0;
utf8proc_ruby_map_error(result);
return Qnil; /* needed to prevent problems with optimization */
}
retval = rb_str_new((char *)env->buffer, result);
free(env->buffer);
env->buffer = 0;
return retval;
}
static VALUE utf8proc_ruby_char(VALUE self, VALUE code_param) {
char buffer[4];
ssize_t result;
int uc;
uc = NUM2INT(code_param);
if (!utf8proc_codepoint_valid(uc))
rb_raise(rb_eArgError, "Invalid Unicode code point");
result = utf8proc_encode_char(uc, buffer);
return rb_str_new(buffer, result);
}
#define register_utf8proc_option(sym, field) \
rb_hash_aset(utf8proc_ruby_options, ID2SYM(rb_intern(sym)), INT2FIX(field))
void Init_utf8proc_native() {
utf8proc_ruby_module = rb_define_module("Utf8Proc");
rb_define_module_function(utf8proc_ruby_module, "utf8map",
utf8proc_ruby_map, 2);
rb_define_module_function(utf8proc_ruby_module, "utf8char",
utf8proc_ruby_char, 1);
utf8proc_ruby_eUnicodeError = rb_define_class_under(utf8proc_ruby_module,
"UnicodeError", rb_eStandardError);
utf8proc_ruby_eInvalidUtf8Error = rb_define_class_under(
utf8proc_ruby_module, "InvalidUtf8Error", utf8proc_ruby_eUnicodeError);
utf8proc_ruby_eCodeNotAssignedError = rb_define_class_under(
utf8proc_ruby_module, "CodeNotAssignedError",
utf8proc_ruby_eUnicodeError);
utf8proc_ruby_options = rb_hash_new();
register_utf8proc_option("stable", UTF8PROC_STABLE);
register_utf8proc_option("compat", UTF8PROC_COMPAT);
register_utf8proc_option("compose", UTF8PROC_COMPOSE);
register_utf8proc_option("decompose", UTF8PROC_DECOMPOSE);
register_utf8proc_option("ignore", UTF8PROC_IGNORE);
register_utf8proc_option("rejectna", UTF8PROC_REJECTNA);
register_utf8proc_option("nlf2ls", UTF8PROC_NLF2LS);
register_utf8proc_option("nlf2ps", UTF8PROC_NLF2PS);
register_utf8proc_option("nlf2lf", UTF8PROC_NLF2LF);
register_utf8proc_option("stripcc", UTF8PROC_STRIPCC);
register_utf8proc_option("casefold", UTF8PROC_CASEFOLD);
register_utf8proc_option("charbound", UTF8PROC_CHARBOUND);
register_utf8proc_option("lump", UTF8PROC_LUMP);
register_utf8proc_option("stripmark", UTF8PROC_STRIPMARK);
OBJ_FREEZE(utf8proc_ruby_options);
rb_define_const(utf8proc_ruby_module, "Options", utf8proc_ruby_options);
}