mirrors/php-src
0
0
Fork 0
mirror of https://github.com/php/php-src.git synced 2024-12-23 00:40:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

- Removed out-of-date comments and one enum constant from html_tables.h and its generator.

Browse Source 
- Other minor aesthetic improvements in the generator.
This commit is contained in:
Gustavo André dos Santos Lopes 2010-10-24 19:05:21 +00:00
parent 3f804701b5
commit 03de44f23e
2 changed files with 68 additions and 85 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
ext/standard/html_tables.h
View File

@ -1,4 +1,4 @@
/* /*
+----------------------------------------------------------------------+ +----------------------------------------------------------------------+
| PHP Version 5 | | PHP Version 5 |
+----------------------------------------------------------------------+ +----------------------------------------------------------------------+
@ -28,17 +28,9 @@
*************************************************************************** ***************************************************************************
**************************************************************************/ **************************************************************************/
/* cs_terminator is overloaded in the following fashion: enum entity_charset { cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15, cs_cp1251,
* - It terminates the list entity maps. cs_8859_5, cs_cp866, cs_macroman, cs_koi8r, cs_big5,
* - In BG(inverse_ent_maps), it's the key of the inverse map that stores cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
* only the basic entities.
* - When passed to traverse_for_entities (or via php_unescape_entities with !all),
* we don't care about the encoding (UTF-8 is chosen, but it should be used
* when it doesn't matter).
*/
enum entity_charset { cs_terminator, cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15,
cs_cp1251, cs_8859_5, cs_cp866, cs_macroman, cs_koi8r,
cs_big5, cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
cs_numelems /* used to count the number of charsets */ cs_numelems /* used to count the number of charsets */
}; };
#define CHARSET_UNICODE_COMPAT(cs) ((cs) <= cs_utf_8) #define CHARSET_UNICODE_COMPAT(cs) ((cs) <= cs_utf_8)
@ -49,36 +41,36 @@ static const struct {
const char *codeset; const char *codeset;
enum entity_charset charset; enum entity_charset charset;
} charset_map[] = { } charset_map[] = {
{ "ISO-8859-1", cs_8859_1 }, { "ISO-8859-1", cs_8859_1 },
{ "ISO8859-1", cs_8859_1 }, { "ISO8859-1", cs_8859_1 },
{ "ISO-8859-15", cs_8859_15 }, { "ISO-8859-15", cs_8859_15 },
{ "ISO8859-15", cs_8859_15 }, { "ISO8859-15", cs_8859_15 },
{ "utf-8", cs_utf_8 }, { "utf-8", cs_utf_8 },
{ "cp1252", cs_cp1252 }, { "cp1252", cs_cp1252 },
{ "Windows-1252", cs_cp1252 }, { "Windows-1252", cs_cp1252 },
{ "1252", cs_cp1252 }, { "1252", cs_cp1252 },
{ "BIG5", cs_big5 }, { "BIG5", cs_big5 },
{ "950", cs_big5 }, { "950", cs_big5 },
{ "GB2312", cs_gb2312 }, { "GB2312", cs_gb2312 },
{ "936", cs_gb2312 }, { "936", cs_gb2312 },
{ "BIG5-HKSCS", cs_big5hkscs }, { "BIG5-HKSCS", cs_big5hkscs },
{ "Shift_JIS", cs_sjis }, { "Shift_JIS", cs_sjis },
{ "SJIS", cs_sjis }, { "SJIS", cs_sjis },
{ "932", cs_sjis }, { "932", cs_sjis },
{ "EUCJP", cs_eucjp }, { "EUCJP", cs_eucjp },
{ "EUC-JP", cs_eucjp }, { "EUC-JP", cs_eucjp },
{ "KOI8-R", cs_koi8r }, { "KOI8-R", cs_koi8r },
{ "koi8-ru", cs_koi8r }, { "koi8-ru", cs_koi8r },
{ "koi8r", cs_koi8r }, { "koi8r", cs_koi8r },
{ "cp1251", cs_cp1251 }, { "cp1251", cs_cp1251 },
{ "Windows-1251", cs_cp1251 }, { "Windows-1251", cs_cp1251 },
{ "win-1251", cs_cp1251 }, { "win-1251", cs_cp1251 },
{ "iso8859-5", cs_8859_5 }, { "iso8859-5", cs_8859_5 },
{ "iso-8859-5", cs_8859_5 }, { "iso-8859-5", cs_8859_5 },
{ "cp866", cs_cp866 }, { "cp866", cs_cp866 },
{ "866", cs_cp866 }, { "866", cs_cp866 },
{ "ibm866", cs_cp866 }, { "ibm866", cs_cp866 },
{ "MacRoman", cs_macroman }, { "MacRoman", cs_macroman },
{ NULL } { NULL }
}; };
@ -475,7 +467,6 @@ static const enc_to_uni enc_to_uni_macroman = {
/* {{{ Index of tables for encoding conversion */ /* {{{ Index of tables for encoding conversion */
static const enc_to_uni *const enc_to_uni_index[cs_numelems] = { static const enc_to_uni *const enc_to_uni_index[cs_numelems] = {
NULL,
NULL, NULL,
&enc_to_uni_iso88591, &enc_to_uni_iso88591,
&enc_to_uni_win1252, &enc_to_uni_win1252,
@ -1144,7 +1135,7 @@ typedef struct {
const entity_stage3_row *table; const entity_stage3_row *table;
} entity_table_opt; } entity_table_opt;
/* Replaced "GT" > "gt" and "QUOT" > "quot" for consistentcy's sake. */ /* Replaced "GT" > "gt" and "QUOT" > "quot" for consistency's sake. */
/* {{{ Start of HTML5 multi-stage table for codepoint -> entity */ /* {{{ Start of HTML5 multi-stage table for codepoint -> entity */

84
ext/standard/html_tables/html_table_gen.php
View File

@ -51,17 +51,9 @@ $t = <<<CODE
*************************************************************************** ***************************************************************************
**************************************************************************/ **************************************************************************/
/* cs_terminator is overloaded in the following fashion: enum entity_charset { cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15, cs_cp1251,
* - It terminates the list entity maps. cs_8859_5, cs_cp866, cs_macroman, cs_koi8r, cs_big5,
* - In BG(inverse_ent_maps), it's the key of the inverse map that stores cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
* only the basic entities.
* - When passed to traverse_for_entities (or via php_unescape_entities with !all),
* we don't care about the encoding (UTF-8 is chosen, but it should be used
* when it doesn't matter).
*/
enum entity_charset { cs_terminator, cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15,
cs_cp1251, cs_8859_5, cs_cp866, cs_macroman, cs_koi8r,
cs_big5, cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
cs_numelems /* used to count the number of charsets */ cs_numelems /* used to count the number of charsets */
}; };
#define CHARSET_UNICODE_COMPAT(cs) ((cs) <= cs_utf_8) #define CHARSET_UNICODE_COMPAT(cs) ((cs) <= cs_utf_8)
@ -72,36 +64,36 @@ static const struct {
const char *codeset; const char *codeset;
enum entity_charset charset; enum entity_charset charset;
} charset_map[] = { } charset_map[] = {
{ "ISO-8859-1", cs_8859_1 }, { "ISO-8859-1", cs_8859_1 },
{ "ISO8859-1", cs_8859_1 }, { "ISO8859-1", cs_8859_1 },
{ "ISO-8859-15", cs_8859_15 }, { "ISO-8859-15", cs_8859_15 },
{ "ISO8859-15", cs_8859_15 }, { "ISO8859-15", cs_8859_15 },
{ "utf-8", cs_utf_8 }, { "utf-8", cs_utf_8 },
{ "cp1252", cs_cp1252 }, { "cp1252", cs_cp1252 },
{ "Windows-1252", cs_cp1252 }, { "Windows-1252", cs_cp1252 },
{ "1252", cs_cp1252 }, { "1252", cs_cp1252 },
{ "BIG5", cs_big5 }, { "BIG5", cs_big5 },
{ "950", cs_big5 }, { "950", cs_big5 },
{ "GB2312", cs_gb2312 }, { "GB2312", cs_gb2312 },
{ "936", cs_gb2312 }, { "936", cs_gb2312 },
{ "BIG5-HKSCS", cs_big5hkscs }, { "BIG5-HKSCS", cs_big5hkscs },
{ "Shift_JIS", cs_sjis }, { "Shift_JIS", cs_sjis },
{ "SJIS", cs_sjis }, { "SJIS", cs_sjis },
{ "932", cs_sjis }, { "932", cs_sjis },
{ "EUCJP", cs_eucjp }, { "EUCJP", cs_eucjp },
{ "EUC-JP", cs_eucjp }, { "EUC-JP", cs_eucjp },
{ "KOI8-R", cs_koi8r }, { "KOI8-R", cs_koi8r },
{ "koi8-ru", cs_koi8r }, { "koi8-ru", cs_koi8r },
{ "koi8r", cs_koi8r }, { "koi8r", cs_koi8r },
{ "cp1251", cs_cp1251 }, { "cp1251", cs_cp1251 },
{ "Windows-1251", cs_cp1251 }, { "Windows-1251", cs_cp1251 },
{ "win-1251", cs_cp1251 }, { "win-1251", cs_cp1251 },
{ "iso8859-5", cs_8859_5 }, { "iso8859-5", cs_8859_5 },
{ "iso-8859-5", cs_8859_5 }, { "iso-8859-5", cs_8859_5 },
{ "cp866", cs_cp866 }, { "cp866", cs_cp866 },
{ "866", cs_cp866 }, { "866", cs_cp866 },
{ "ibm866", cs_cp866 }, { "ibm866", cs_cp866 },
{ "MacRoman", cs_macroman }, { "MacRoman", cs_macroman },
{ NULL } { NULL }
}; };
@ -132,51 +124,51 @@ echo $t;
$encodings = array( $encodings = array(
array( array(
"ident" => "iso88591", "ident" => "iso88591",
"enumid" => 2, "enumid" => 1,
"name" => "ISO-8859-1", "name" => "ISO-8859-1",
"file" => "mappings/8859-1.TXT", "file" => "mappings/8859-1.TXT",
), ),
array( array(
"ident" => "iso88595", "ident" => "iso88595",
"enumid" => 6, "enumid" => 5,
"name" => "ISO-8859-5", "name" => "ISO-8859-5",
"file" => "mappings/8859-5.TXT", "file" => "mappings/8859-5.TXT",
), ),
array( array(
"ident" => "iso885915", "ident" => "iso885915",
"enumid" => 4, "enumid" => 3,
"name" => "ISO-8859-15", "name" => "ISO-8859-15",
"file" => "mappings/8859-15.TXT", "file" => "mappings/8859-15.TXT",
), ),
array( array(
"ident" => "win1252", "ident" => "win1252",
"enumid" => 3, "enumid" => 2,
"enumident" => "cp1252", "enumident" => "cp1252",
"name" => "Windows-1252", "name" => "Windows-1252",
"file" => "mappings/CP1252.TXT", "file" => "mappings/CP1252.TXT",
), ),
array( array(
"ident" => "win1251", "ident" => "win1251",
"enumid" => 5, "enumid" => 4,
"enumident" => "cp1252", "enumident" => "cp1252",
"name" => "Windows-1251", "name" => "Windows-1251",
"file" => "mappings/CP1251.TXT", "file" => "mappings/CP1251.TXT",
), ),
array( array(
"ident" => "koi8r", "ident" => "koi8r",
"enumid" => 9, "enumid" => 8,
"name" => "KOI8-R", "name" => "KOI8-R",
"file" => "mappings/KOI8-R.TXT", "file" => "mappings/KOI8-R.TXT",
), ),
array( array(
"ident" => "cp866", "ident" => "cp866",
"enumid" => 7, "enumid" => 6,
"name" => "CP-866", "name" => "CP-866",
"file" => "mappings/CP866.TXT", "file" => "mappings/CP866.TXT",
), ),
array( array(
"ident" => "macroman", "ident" => "macroman",
"enumid" => 8, "enumid" => 7,
"name" => "MacRoman", "name" => "MacRoman",
"file" => "mappings/ROMAN.TXT", "file" => "mappings/ROMAN.TXT",
), ),
@ -336,7 +328,7 @@ foreach ($encodings as $e) {
$lines = explode("\n", file_get_contents($e{'file'})); $lines = explode("\n", file_get_contents($e{'file'}));
foreach ($lines as $l) { foreach ($lines as $l) {
if (preg_match("/^0x([0-9A-Z]{2})\t0x([0-9A-Z]{2,})\s+#\s*(.*)$/i", $l, $matches)) if (preg_match("/^0x([0-9A-Z]{2})\t0x([0-9A-Z]{2,})\s+#\s*(.*)$/i", $l, $matches))
$map[] = array($matches[1], $matches[2], $matches[3]); $map[] = array($matches[1], $matches[2], rtrim($matches[3]));
} }
$mappy = array(); $mappy = array();
@ -420,7 +412,7 @@ typedef struct {
const entity_stage3_row *table; const entity_stage3_row *table;
} entity_table_opt; } entity_table_opt;
/* Replaced "GT" > "gt" and "QUOT" > "quot" for consistentcy's sake. */ /* Replaced "GT" > "gt" and "QUOT" > "quot" for consistency's sake. */
CODE; CODE;