Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit16c302f

Browse files
committed
Simplify code for getting a unicode codepoint's canonical class.
Three places of unicode_norm.c use a similar logic for getting thecombining class from a codepoint. Commit2991ac5 has added the functionget_canonical_class() for this purpose, but it was only called by thebackend. This commit refactors the code to use this function in allthe places where the combining class is retrieved from a givencodepoint.Author: John NaylorDiscussion:https://postgr.es/m/CAFBsxsHUV7s7YrOm6hFz-Jq8Sc7K_yxTkfNZxsDV-DuM-k-gwg@mail.gmail.com
1 parentdf99ddc commit16c302f

File tree

1 file changed

+22
-25
lines changed

1 file changed

+22
-25
lines changed

‎src/common/unicode_norm.c

Lines changed: 22 additions & 25 deletions
Original file line numberDiff line numberDiff line change
@@ -105,6 +105,23 @@ get_code_entry(pg_wchar code)
105105
#endif
106106
}
107107

108+
/*
109+
* Get the combining class of the given codepoint.
110+
*/
111+
staticuint8
112+
get_canonical_class(pg_wcharcode)
113+
{
114+
constpg_unicode_decomposition*entry=get_code_entry(code);
115+
116+
/*
117+
* If no entries are found, the character used is either an Hangul
118+
* character or a character with a class of 0 and no decompositions.
119+
*/
120+
if (!entry)
121+
return0;
122+
else
123+
returnentry->comb_class;
124+
}
108125

109126
/*
110127
* Given a decomposition entry looked up earlier, get the decomposed
@@ -430,16 +447,8 @@ unicode_normalize(UnicodeNormalizationForm form, const pg_wchar *input)
430447
pg_wcharprev=decomp_chars[count-1];
431448
pg_wcharnext=decomp_chars[count];
432449
pg_wchartmp;
433-
constpg_unicode_decomposition*prevEntry=get_code_entry(prev);
434-
constpg_unicode_decomposition*nextEntry=get_code_entry(next);
435-
436-
/*
437-
* If no entries are found, the character used is either an Hangul
438-
* character or a character with a class of 0 and no decompositions,
439-
* so move to next result.
440-
*/
441-
if (prevEntry==NULL||nextEntry==NULL)
442-
continue;
450+
constuint8prevClass=get_canonical_class(prev);
451+
constuint8nextClass=get_canonical_class(next);
443452

444453
/*
445454
* Per Unicode (https://www.unicode.org/reports/tr15/tr15-18.html)
@@ -449,10 +458,10 @@ unicode_normalize(UnicodeNormalizationForm form, const pg_wchar *input)
449458
* combining class for the second, and the second is not a starter. A
450459
* character is a starter if its combining class is 0.
451460
*/
452-
if (nextEntry->comb_class==0x0||prevEntry->comb_class==0x0)
461+
if (prevClass==0||nextClass==0)
453462
continue;
454463

455-
if (prevEntry->comb_class <=nextEntry->comb_class)
464+
if (prevClass <=nextClass)
456465
continue;
457466

458467
/* exchange can happen */
@@ -489,8 +498,7 @@ unicode_normalize(UnicodeNormalizationForm form, const pg_wchar *input)
489498
for (count=1;count<decomp_size;count++)
490499
{
491500
pg_wcharch=decomp_chars[count];
492-
constpg_unicode_decomposition*ch_entry=get_code_entry(ch);
493-
intch_class= (ch_entry==NULL) ?0 :ch_entry->comb_class;
501+
intch_class=get_canonical_class(ch);
494502
pg_wcharcomposite;
495503

496504
if (last_class<ch_class&&
@@ -527,17 +535,6 @@ unicode_normalize(UnicodeNormalizationForm form, const pg_wchar *input)
527535
/* We only need this in the backend. */
528536
#ifndefFRONTEND
529537

530-
staticuint8
531-
get_canonical_class(pg_wcharch)
532-
{
533-
constpg_unicode_decomposition*entry=get_code_entry(ch);
534-
535-
if (!entry)
536-
return0;
537-
else
538-
returnentry->comb_class;
539-
}
540-
541538
staticconstpg_unicode_normprops*
542539
qc_hash_lookup(pg_wcharch,constpg_unicode_norminfo*norminfo)
543540
{

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp