-
Notifications
You must be signed in to change notification settings - Fork 7.9k
[RFC] Add trim for multibyte function #12459
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
Closed
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,125 @@ | ||
| --TEST-- | ||
| mb_trim() function tests | ||
| --EXTENSIONS-- | ||
| mbstring | ||
| --FILE-- | ||
| <?php | ||
| mb_internal_encoding("UTF-8"); | ||
|
|
||
| echo "== Copy from trim ==\n"; | ||
| var_dump('ABC' === mb_trim('ABC')); | ||
| var_dump('ABC' === mb_ltrim('ABC')); | ||
| var_dump('ABC' === mb_rtrim('ABC')); | ||
| var_dump('ABC' === mb_trim(" \0\t\nABC \0\t\n")); | ||
| var_dump("ABC \0\t\n" === mb_ltrim(" \0\t\nABC \0\t\n")); | ||
| var_dump(" \0\t\nABC" === mb_rtrim(" \0\t\nABC \0\t\n")); | ||
| var_dump(" \0\t\nABC \0\t\n" === mb_trim(" \0\t\nABC \0\t\n",'')); | ||
| var_dump(" \0\t\nABC \0\t\n" === mb_ltrim(" \0\t\nABC \0\t\n",'')); | ||
| var_dump(" \0\t\nABC \0\t\n" === mb_rtrim(" \0\t\nABC \0\t\n",'')); | ||
| echo "== Empty string ==\n"; | ||
| var_dump(mb_trim("")); | ||
| var_dump(mb_ltrim("")); | ||
| var_dump(mb_rtrim("")); | ||
|
|
||
| echo "== Single string ==\n"; | ||
youkidearitai marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| var_dump(mb_ltrim(' test ', '')); | ||
| var_dump(mb_trim(" あいうえおあお ", " ", "UTF-8")); | ||
| var_dump(mb_trim('foo BAR Spaß', 'ß', "UTF-8")); | ||
| var_dump(mb_trim('foo BAR Spaß', 'f', "UTF-8")); | ||
|
|
||
| echo "== Multi strings ==\n"; | ||
| var_dump(mb_trim('foo BAR Spaß', 'ßf', "UTF-8")); | ||
| var_dump(mb_trim('foo BAR Spaß', 'fß', "UTF-8")); | ||
| var_dump(mb_trim(" あいうおえお あ", " あ", "UTF-8")); | ||
| var_dump(mb_trim(" あいうおえお あ", "あ ", "UTF-8")); | ||
| var_dump(mb_trim(" あいうおえお a", "あa", "UTF-8")); | ||
| var_dump(mb_trim(" あいうおえお a", "\xe3", "UTF-8")); | ||
|
|
||
| echo "== Many strings ==\n"; | ||
| var_dump(mb_trim(str_repeat(" ", 129))); | ||
| var_dump(mb_trim(str_repeat(" ", 129) . "a")); | ||
| var_dump(mb_rtrim(str_repeat(" ", 129) . "a")); | ||
|
|
||
| echo "== mb_ltrim ==\n"; | ||
| var_dump(mb_ltrim("あああああああああああああああああああああああああああああああああいああああ", "あ")); | ||
| echo "== mb_rtrim ==\n"; | ||
| var_dump(mb_rtrim("あああああああああああああああああああああああああああああああああいああああ", "あ")); | ||
|
|
||
| echo "== default params ==\n"; | ||
| var_dump(mb_trim(" \f\n\r\v\x00\u{00A0}\u{1680}\u{2000}\u{2001}\u{2002}\u{2003}\u{2004}\u{2005}\u{2006}\u{2007}\u{2008}\u{2009}\u{200A}\u{2028}\u{2029}\u{202F}\u{205F}\u{3000}\u{0085}\u{180E}")); | ||
|
|
||
| echo "== Byte Order Mark ==\n"; | ||
| var_dump(mb_ltrim("\u{FFFE}漢字", "\u{FFFE}\u{FEFF}")); | ||
| var_dump(bin2hex(mb_ltrim(mb_convert_encoding("\u{FFFE}漢字", "UTF-16LE", "UTF-8"), mb_convert_encoding("\u{FFFE}\u{FEFF}", "UTF-16LE", "UTF-8"), "UTF-16LE"))); | ||
| var_dump(bin2hex(mb_ltrim(mb_convert_encoding("\u{FEFF}漢字", "UTF-16BE", "UTF-8"), mb_convert_encoding("\u{FFFE}\u{FEFF}", "UTF-16BE", "UTF-8"), "UTF-16BE"))); | ||
|
|
||
| echo "== Empty string ==\n"; | ||
| var_dump(mb_trim(" abcd ", "")); | ||
| var_dump(mb_ltrim(" abcd ", "")); | ||
| var_dump(mb_rtrim(" abcd ", "")); | ||
|
|
||
| echo "== SJIS ==\n"; | ||
| var_dump(mb_convert_encoding(mb_trim("\x81\x40\x82\xa0\x81\x40", "\x81\x40", "SJIS"), "UTF-8", "SJIS")); | ||
|
|
||
| echo "== Same strings ==\n"; | ||
| var_dump(mb_trim("foo", "oo")); | ||
|
|
||
| echo "== \$encoding throws ValueError ==\n"; | ||
| try { | ||
| var_dump(mb_trim( "\u{180F}", "", "NULL")); | ||
| } catch (ValueError $e) { | ||
| var_dump($e->getMessage()); | ||
| } | ||
|
|
||
| ?> | ||
| --EXPECT-- | ||
| == Copy from trim == | ||
| bool(true) | ||
| bool(true) | ||
| bool(true) | ||
| bool(true) | ||
| bool(true) | ||
| bool(true) | ||
| bool(true) | ||
| bool(true) | ||
| bool(true) | ||
| == Empty string == | ||
| string(0) "" | ||
| string(0) "" | ||
| string(0) "" | ||
| == Single string == | ||
| string(6) " test " | ||
| string(21) "あいうえおあお" | ||
| string(11) "foo BAR Spa" | ||
| string(12) "oo BAR Spaß" | ||
| == Multi strings == | ||
| string(10) "oo BAR Spa" | ||
| string(10) "oo BAR Spa" | ||
| string(16) "いうおえお " | ||
| string(16) "いうおえお " | ||
| string(25) " あいうおえお " | ||
| string(26) " あいうおえお a" | ||
| == Many strings == | ||
| string(0) "" | ||
| string(1) "a" | ||
| string(388) " a" | ||
| == mb_ltrim == | ||
| string(15) "いああああ" | ||
| == mb_rtrim == | ||
| string(102) "あああああああああああああああああああああああああああああああああい" | ||
| == default params == | ||
| string(0) "" | ||
| == Byte Order Mark == | ||
| string(6) "漢字" | ||
| string(8) "226f575b" | ||
| string(8) "6f225b57" | ||
| == Empty string == | ||
| string(6) " abcd " | ||
| string(6) " abcd " | ||
| string(6) " abcd " | ||
| == SJIS == | ||
| string(3) "あ" | ||
| == Same strings == | ||
| string(1) "f" | ||
| == $encoding throws ValueError == | ||
| string(73) "mb_trim(): Argument #3 ($encoding) must be a valid encoding, "NULL" given" | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hmm, just thinking about this. Is it true that most mbstring functions take the encoding last as an optional parameter? If so, then this is good. 👍🏻
It just means that if a user wants to pass an explicit encoding, they have to pass the list of whitespace chars as well. If the order was
(str, encoding, what), then the user could pass an explicit encoding, but use the default value ofwhat.What do you think is better?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
(If this was already discussed at the RFC stage, then please disregard my comment.)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just my 2c: The mbstring functions take encoding as last. If you don't want to pass
whatthen you can use named arguments:mb_trim("my string", encoding: "GB18030")for example.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
As @nielsdos said, I am assuming to use
mb_trim("my string", encoding: "GB18030");