Module:Unicode data/sandbox
See also the companion subpage for test cases (run).
1 of 110 tests failed.
testcases for get_best_script
| Text | Expected | Actual | |
|---|---|---|---|
| checkY | %!?́: Zyyy (3), Zinh (1) | nil | nil |
| checkY | ’ʼ""†‡•‰′‽⁕ • Zyyy (11) |
nil | nil |
| checkY | col·legi: Latn (7), Zyyy (1) | Latn | Latn |
| HTML character references | |||
| checkY | 𐘀: Lina (1) | Lina | Lina |
| checkY | 𐘀 • Zyyy (8), Latn (1) |
Lina | Lina |
| checkY | – • Zyyy (1) |
nil | nil |
| checkY | – • Latn (5), Zyyy (2) |
nil | nil |
| Halkomelem | |||
| checkY | lá:yelhp: Latn (7), Zyyy (1) | Latn | Latn |
| checkY | xwməθkwəy̓əm: Latn (10), Grek (1), Zinh (1) | nil | nil |
| checkY | hən̓q̓əmin̓əm̓: Latn (10), Zinh (4) | Latn | Latn |
| Quotes | |||
| checkY | Tant’è amara che poco è più morte; ma per trattar del ben ch’i’ vi trovai, dirò de l’altre cose ch’i’ v’ ho scorte. • Latn (83), Zyyy (32) |
Latn | Latn |
| checkY | Díí Késhmish biyiʼ yáʼąąshdę́ę́ʼ ląʼígóó bee nikʼihojidlíi dooleeł. Niheechʼínáánáháhígíí biyiʼ iłhodeezyéél, iłhózhǫ́, ayóóʼóʼóʼní bee nikʼihojidlíi dooleeł. Tʼáá sahdiigiʼ átʼéego baa hózhǫ́ǫgo nihił hanááhoolzhiizhígí biyiʼ tʼáá ałtsojįʼ iłhózhǫ́ nííʼ dooleeł. • Latn (207), Zyyy (52), Zinh (5) |
Latn | Latn |
| checkY | Μῆνῐν ᾰ̓́ειδε, θεᾱ́, Πηληῐ̈ᾰ́δεω Ᾰ̓χῐλῆος οὐλομένην, ἣ μῡρῐ́ ̓ Ᾰ̓χαιοῖς ᾰ̓́λγε ̓ ἔθηκε, πολλᾱ̀ς δ ̓ ῐ̓φθῑ́μους ψῡχᾱ̀ς Ἄῐ̈δῐ προῐ̈́ᾰψεν ἡρώων, αὐτοὺς δὲ ἑλώρῐᾰ τεῦχε κῠ́νεσσιν οἰωνοῖσῐ́ τε πᾶσῐ· Δῐὸς δ ̓ ἐτελείετο βουλή· • Grek (160), Zyyy (36), Zinh (19) |
Grek | Grek |
| checkY | Вот если вы не согласитесь с этим последним тезисом и ответите: «Не так» или «не всегда так», то я, пожалуй, и ободрюсь духом насчет значения героя моего Алексея Федоровича. Ибо не только чудак «не всегда» частность и обособление, а напротив, бывает так, что он-то, пожалуй, и носит в себе иной раз сердцевину целого, а остальные люди его эпохи — все, каким-нибудь наплывным ветром, на время почему-то от него оторвались... • Cyrl (329), Zyyy (93) |
Cyrl | Cyrl |
| checkY | ॐ अग्निमीळे पुरोहितं यज्ञस्य देवमृत्विजम् । होतारं रत्नधातमम् ॥१॥ अग्निः पूर्वेभिरृषिभिरीड्यो नूतनैरुत । स देवाँ एह वक्षति ॥२॥ अग्निना रयिमश्नवत् पोषमेव दिवेदिवे । यशसं वीरवत्तमम् ॥३॥ अग्ने यं यज्ञमध्वरं विश्वतः परिभूरसि । स इद्देवेषु गच्छति ॥४॥ अग्निर्होता कविक्रतुः सत्यश्चित्रश्रवस्तमः । देवो देवेभिरा गमत् ॥५॥ यदङ्ग दाशुषे त्वमग्ने भद्रं करिष्यसि । तवेत् तत् सत्यमङ्गिरः ॥६॥ उप त्वाग्ने दिवेदिवे दोषावस्तर्धिया वयम् । नमो भरन्त एमसि ॥७॥ राजन्तमध्वराणां गोपामृतस्य दीदिविम् । वर्धमानं स्वे दमे ॥८॥ स नः पितेव सूनवेऽग्ने सूपायनो भव । सचस्वा नः स्वस्तये ॥९॥ • Deva (449), Zyyy (109) |
Deva | Deva |
testcases for is_Latin
| Text | Expected | Actual | |
|---|---|---|---|
| checkY | %!?́: Zyyy (3), Zinh (1) | false | false |
| checkY | ’ʼ""†‡•‰′‽⁕ • Zyyy (11) |
false | false |
| checkY | col·legi: Latn (7), Zyyy (1) | true | true |
| HTML character references | |||
| checkY | 𐘀: Lina (1) | false | false |
| checkY | 𐘀 • Zyyy (8), Latn (1) |
false | false |
| checkY | – • Zyyy (1) |
false | false |
| checkY | – • Latn (5), Zyyy (2) |
false | false |
| Halkomelem | |||
| checkY | lá:yelhp: Latn (7), Zyyy (1) | true | true |
| checkY | xwməθkwəy̓əm: Latn (10), Grek (1), Zinh (1) | false | false |
| checkY | hən̓q̓əmin̓əm̓: Latn (10), Zinh (4) | true | true |
| Quotes | |||
| checkY | Tant’è amara che poco è più morte; ma per trattar del ben ch’i’ vi trovai, dirò de l’altre cose ch’i’ v’ ho scorte. • Latn (83), Zyyy (32) |
true | true |
| checkY | Díí Késhmish biyiʼ yáʼąąshdę́ę́ʼ ląʼígóó bee nikʼihojidlíi dooleeł. Niheechʼínáánáháhígíí biyiʼ iłhodeezyéél, iłhózhǫ́, ayóóʼóʼóʼní bee nikʼihojidlíi dooleeł. Tʼáá sahdiigiʼ átʼéego baa hózhǫ́ǫgo nihił hanááhoolzhiizhígí biyiʼ tʼáá ałtsojįʼ iłhózhǫ́ nííʼ dooleeł. • Latn (207), Zyyy (52), Zinh (5) |
true | true |
| checkY | Μῆνῐν ᾰ̓́ειδε, θεᾱ́, Πηληῐ̈ᾰ́δεω Ᾰ̓χῐλῆος οὐλομένην, ἣ μῡρῐ́ ̓ Ᾰ̓χαιοῖς ᾰ̓́λγε ̓ ἔθηκε, πολλᾱ̀ς δ ̓ ῐ̓φθῑ́μους ψῡχᾱ̀ς Ἄῐ̈δῐ προῐ̈́ᾰψεν ἡρώων, αὐτοὺς δὲ ἑλώρῐᾰ τεῦχε κῠ́νεσσιν οἰωνοῖσῐ́ τε πᾶσῐ· Δῐὸς δ ̓ ἐτελείετο βουλή· • Grek (160), Zyyy (36), Zinh (19) |
false | false |
| checkY | Вот если вы не согласитесь с этим последним тезисом и ответите: «Не так» или «не всегда так», то я, пожалуй, и ободрюсь духом насчет значения героя моего Алексея Федоровича. Ибо не только чудак «не всегда» частность и обособление, а напротив, бывает так, что он-то, пожалуй, и носит в себе иной раз сердцевину целого, а остальные люди его эпохи — все, каким-нибудь наплывным ветром, на время почему-то от него оторвались... • Cyrl (329), Zyyy (93) |
false | false |
| checkY | ॐ अग्निमीळे पुरोहितं यज्ञस्य देवमृत्विजम् । होतारं रत्नधातमम् ॥१॥ अग्निः पूर्वेभिरृषिभिरीड्यो नूतनैरुत । स देवाँ एह वक्षति ॥२॥ अग्निना रयिमश्नवत् पोषमेव दिवेदिवे । यशसं वीरवत्तमम् ॥३॥ अग्ने यं यज्ञमध्वरं विश्वतः परिभूरसि । स इद्देवेषु गच्छति ॥४॥ अग्निर्होता कविक्रतुः सत्यश्चित्रश्रवस्तमः । देवो देवेभिरा गमत् ॥५॥ यदङ्ग दाशुषे त्वमग्ने भद्रं करिष्यसि । तवेत् तत् सत्यमङ्गिरः ॥६॥ उप त्वाग्ने दिवेदिवे दोषावस्तर्धिया वयम् । नमो भरन्त एमसि ॥७॥ राजन्तमध्वराणां गोपामृतस्य दीदिविम् । वर्धमानं स्वे दमे ॥८॥ स नः पितेव सूनवेऽग्ने सूपायनो भव । सचस्वा नः स्वस्तये ॥९॥ • Deva (449), Zyyy (109) |
false | false |
testcases for is_combining
| Text | Expected | Actual | |
|---|---|---|---|
| checkY | U+0300: ◌̀ (COMBINING GRAVE ACCENT) | true | true |
| checkY | U+0060: ` (GRAVE ACCENT) | false | false |
testcases for is_default_ignorable
| Text | Expected | Actual |
|---|
testcases for is_rtl
| Text | Expected | Actual | |
|---|---|---|---|
| checkY | أبو عبد الله محمد بن عبد الله اللواتي الطنجي بن بطوطة | true | true |
| checkY | أدب القاضي Adab al-qādī | false | false |
| checkY | ܛܘܼܒܲܝܗܘܿܢ ܠܐܲܝܠܹܝܢ ܕܲܕ݂ܟܹܝܢ ܒܠܸܒ̇ܗܘܿܢ܄ ܕܗܸܢ݂ܘܿܢ ܢܸܚܙܘܿܢ ܠܐܲܠܵܗܵܐ܂ | true | true |
| checkY | בְּרֵאשִׁית, בָּרָא אֱלֹהִים, אֵת הַשָּׁמַיִם, וְאֵת הָאָרֶץ. | true | true |
| checkY | 𞤀𞤣𞤤𞤢𞤥 𞤆𞤵𞤤𞤢𞤪 | true | true |
| checkY | 𐬬𐬍𐬯𐬞𐬈 ⸱ 𐬰𐬍 ⸱ 𐬀𐬥𐬌𐬌𐬉 ⸱ 𐬨𐬀𐬜𐬃𐬢𐬵𐬋 ⸱ 𐬀𐬉𐬴𐬨𐬀 ⸱ 𐬵𐬀𐬗𐬌𐬧𐬙𐬈 ⸱ 𐬑𐬭𐬎𐬎𐬍𐬨 ⸱ 𐬛𐬭𐬎𐬎𐬋 ⸱ 𐬁𐬀𐬝 ⸱ 𐬵𐬋 ⸱ 𐬫𐬋 ⸱ 𐬵𐬀𐬊𐬨𐬀𐬵𐬈 ⸱ 𐬨𐬀𐬜𐬋 ⸱ 𐬀𐬴𐬀 ⸱ 𐬵𐬀𐬗𐬀𐬌𐬙𐬈 | true | true |
| checkY | ދިވެހި | true | true |
| checkY | 𐤀𐤓𐤍𐤟𐤆𐤐𐤏𐤋𐤟𐤀𐤕𐤁𐤏𐤋𐤟𐤁𐤍𐤀𐤇𐤓𐤌𐤟𐤌𐤋𐤊𐤂𐤁𐤋𐤟𐤋𐤀𐤇𐤓𐤌𐤟𐤀𐤁𐤄 | true | true |
| checkY | ࡌࡀࡍࡃࡀ ࡖࡄࡉࡉࡀ | true | true |
| checkY | ࠄࠟࠓࠂࠝࠓࠜࠉࠆࠜࠉࠌ | true | true |
| checkY | %$!^& | false | false |
testcases for lookup_age
| Text | Expected | Actual |
|---|
testcases for lookup_block
| Text | Expected | Actual | |
|---|---|---|---|
| checkY | U+0064: d | Basic Latin | Basic Latin |
| checkY | U+030B: ◌̋ | Combining Diacritical Marks | Combining Diacritical Marks |
| checkY | U+03A3: Σ | Greek and Coptic | Greek and Coptic |
| checkY | U+0411: Б | Cyrillic | Cyrillic |
| checkY | U+10E6: ღ | Georgian | Georgian |
| checkY | U+3175: ᄣ | Hangul Compatibility Jamo | Hangul Compatibility Jamo |
| checkY | U+AC01: 각 | Hangul Syllables | Hangul Syllables |
| checkY | U+4E0A: 上 | CJK Unified Ideographs | CJK Unified Ideographs |
| checkY | U+1F608: 😈 | Emoticons | Emoticons |
| checkY | U+30000: 𰀀 | CJK Unified Ideographs Extension G | CJK Unified Ideographs Extension G |
| checkY | U+10FFFF | Supplementary Private Use Area-B | Supplementary Private Use Area-B |
testcases for lookup_category
| Text | Expected | Actual | |
|---|---|---|---|
| checkY | U+0009 (<control-0009>) | Cc | Cc |
| checkY | U+0020: (SPACE) | Zs | Zs |
| checkY | U+005B: [ (LEFT SQUARE BRACKET) | Ps | Ps |
| checkY | U+005D: ] (RIGHT SQUARE BRACKET) | Pe | Pe |
| checkY | U+005E: ^ (CIRCUMFLEX ACCENT) | Sk | Sk |
| checkY | U+0041: A (LATIN CAPITAL LETTER A) | Lu | Lu |
| checkY | U+00AD (SOFT HYPHEN) | Cf | Cf |
| checkY | U+00BE: 3⁄4 (VULGAR FRACTION THREE QUARTERS) | No | No |
| checkY | U+00AB: « (LEFT-POINTING DOUBLE ANGLE QUOTATION MARK) | Pi | Pi |
| checkY | U+00BB: » (RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK) | Pf | Pf |
| checkY | U+0300: ◌̀ (COMBINING GRAVE ACCENT) | Mn | Mn |
| checkY | U+0488: ҈ (COMBINING CYRILLIC HUNDRED THOUSANDS SIGN) | Me | Me |
| checkY | U+0663: ٣ (ARABIC-INDIC DIGIT THREE) | Nd | Nd |
| checkY | U+5B50: 子 (CJK UNIFIED IDEOGRAPH-5B50) | Lo | Lo |
| checkY | U+1FAE: ᾮ (GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI) | Lt | Lt |
| checkY | U+1B44: ◌᭄ (BALINESE ADEG ADEG) | Mc | Mc |
| checkY | U+2208: ∈ (ELEMENT OF) | Sm | Sm |
| checkY | U+203F: ‿ (UNDERTIE) | Pc | Pc |
| checkY | U+21B9: ↹ (LEFTWARDS ARROW TO BAR OVER RIGHTWARDS ARROW TO BAR) | So | So |
| checkY | U+2E17: ⸗ (DOUBLE OBLIQUE HYPHEN) | Pd | Pd |
| checkY | U+2167: VIII (ROMAN NUMERAL EIGHT) | Nl | Nl |
| checkY | U+2028 (LINE SEPARATOR) | Zl | Zl |
| checkY | U+2029 (PARAGRAPH SEPARATOR) | Zp | Zp |
| checkY | U+309E: ゞ (HIRAGANA VOICED ITERATION MARK) | Lm | Lm |
| checkY | U+D800 (<surrogate-D800>) | Cs | Cs |
| checkY | U+FFE1: £ (FULLWIDTH POUND SIGN) | Sc | Sc |
| ☒N | U+FFFF (<noncharacter-FFFF>) | Cn | nil |
| checkY | U+100000 (<private-use-100000>) | Co | Co |
testcases for lookup_name
| Text | Expected | Actual | |
|---|---|---|---|
| checkY | U+0000 | <control-0000> | <control-0000> |
| checkY | U+007F | <control-007F> | <control-007F> |
| checkY | U+00C1: Á | LATIN CAPITAL LETTER A WITH ACUTE | LATIN CAPITAL LETTER A WITH ACUTE |
| checkY | U+0300: ◌̀ | COMBINING GRAVE ACCENT | COMBINING GRAVE ACCENT |
| checkY | U+0378 | <reserved-0378> | <reserved-0378> |
| checkY | U+1B44: ◌᭄ | BALINESE ADEG ADEG | BALINESE ADEG ADEG |
| checkY | U+1F71: ά | GREEK SMALL LETTER ALPHA WITH OXIA | GREEK SMALL LETTER ALPHA WITH OXIA |
| checkY | U+3555: 㕕 | CJK UNIFIED IDEOGRAPH-3555 | CJK UNIFIED IDEOGRAPH-3555 |
| checkY | U+AC01: 각 | HANGUL SYLLABLE GAG | HANGUL SYLLABLE GAG |
| checkY | U+D5FF: 헿 | HANGUL SYLLABLE HEH | HANGUL SYLLABLE HEH |
| checkY | U+DC00 | <surrogate-DC00> | <surrogate-DC00> |
| checkY | U+EEEE | <private-use-EEEE> | <private-use-EEEE> |
| checkY | U+FE04: ︄ | VARIATION SELECTOR-5 | VARIATION SELECTOR-5 |
| checkY | U+FDD1 | <noncharacter-FDD1> | <noncharacter-FDD1> |
| checkY | U+FFFD: � | REPLACEMENT CHARACTER | REPLACEMENT CHARACTER |
| checkY | U+FFFF | <noncharacter-FFFF> | <noncharacter-FFFF> |
| checkY | U+1F4A9: 💩 | PILE OF POO | PILE OF POO |
| checkY | U+2ED9D: | CJK UNIFIED IDEOGRAPH-2ED9D | CJK UNIFIED IDEOGRAPH-2ED9D |
| checkY | U+E0000 | <reserved-E0000> | <reserved-E0000> |
| checkY | U+F0F0F | <private-use-F0F0F> | <private-use-F0F0F> |
| checkY | U+10FFFF | <noncharacter-10FFFF> | <noncharacter-10FFFF> |
testcases for lookup_script
| Text | Expected | Actual | |
|---|---|---|---|
| checkY | U+0061: a (LATIN SMALL LETTER A) | Latn | Latn |
| checkY | U+002F: / (SOLIDUS) | Zyyy | Zyyy |
| checkY | U+0300: ◌̀ (COMBINING GRAVE ACCENT) | Zinh | Zinh |
| checkY | U+0378 (<reserved-0378>) | Zzzz | Zzzz |
| checkY | U+0398: Θ (GREEK CAPITAL LETTER THETA) | Grek | Grek |
| checkY | U+03E2: Ϣ (COPTIC CAPITAL LETTER SHEI) | Copt | Copt |
| checkY | U+2014: — (EM DASH) | Zyyy | Zyyy |
Usage
[edit ]This module provides functions that access information on Unicode code points. The information is retrieved from data modules generated from the Unicode Character Database, or derived by rules given in the Unicode Specification. It and its submodules were copied from English Wiktionary and then modified; see there for more information.
Parameters and functions
[edit ]code point
[edit ]The code point is to be entered as hexadecimal value. For example, U+00A9 © COPYRIGHT SIGN:
- |A9hex
- |0xA9hex
- |0x00A9hex
- |0x00a9hex
{{#invoke:Unicode data|lookup|name|0x00A9}}→ COPYRIGHT SIGN
Incorrect or unintended results:
- 169dec:
{{#invoke:Unicode data|lookup|name|169}}→ LATIN SMALL LETTER U WITH TILDE Red XN —"U+00A9"©expected; but is read as 00A9hex (that is, 361dec - U+00A9
{{#invoke:Unicode data|lookup|name|U+00A9}}Red XN —do not use "U+" prefix - غ
{{#invoke:Unicode data|lookup|name|غ}}Red XN —cannot enter a character as codepoint
"lookup" and "is" functions
[edit ]lookup,is- Template-invokable functions that allow access to the functions starting with
lookupandis.For most of the functions, add the code point in hexadecimal base as the next parameter. Foris|Latin,is|rtl, andis|valid_pagename, add character string. HTML character references in the text are decoded by the module into code points. - For example,
{{#invoke:Unicode data|is|Latin|àzàhàr̃iyyā̀}}→ true.
- Internally, in modules, these functions are named using underscore:
lookup_name|codepoint←lookup_name - For
&A9;©:{{#invoke:Unicode data|lookup|name|A9}}→ COPYRIGHT SIGN
Functions overview
[edit ]- Code points: enter hexadecimal value, for example |0x0061 or |61; not |U+0061.
| Topic | Function | Parameter type (string=by character(s); c.p. by 0xHex value) |
Example | Returns | Character |
|---|---|---|---|---|---|
| Unicode character name | |lookup|name
|
code point |
|
|
|
| Scripts | |lookup|script
|
code point | {{#invoke:Unicode data|lookup|script|A061}}
|
Yiii |
|
| Blocks | |lookup|block
|
code point | {{#invoke:Unicode data|lookup|block|A061}}
|
Yi Syllables |
|
| Planes | |lookup|plane
|
code point |
|
|
|
| General Category | |lookup|category
|
code point |
|
|
|
| Controls | |is|control
|
code point |
|
|
|
| Unihan properties | |lookup|kCantonese
|
code point |
|
|
|
| Latin script | |is|Latin
|
string |
|
|
|
| WP:Article title (WP:NCTR) | |is|valid_pagename
|
string |
|
|
|
| Bidirectionality, right-to-left scripts | |is|rtl
|
string |
|
|
|
| Combining character | |is|combining
|
code point |
|
|
|
| Character assignation | |is|assigned
|
code point |
|
|
|
| Printable | |is|printable
|
code point |
|
|
|
| Whitespace character § Unicode | |is|whitespace
|
code point |
|
|
|
| Alias names | |aliases
|
[application unknown] |
| ||
| Combining class | |
|
[application unknown] |
| ||
| Age | |
|
[application unknown] | |||
| get_best_script | |get_best_script
|
[application unknown] |
Data modules
[edit ]The data used by functions in this module is found in submodules. Some are generated by AWK scripts shown at User:Kephir/Unicode on English Wiktionary, others by Lua scripts on the /make subpages of the submodules.
- Module:Unicode data/age: 'Age' of a character, that is: version introduction number.
- Module:Unicode data/aliases: the formal name aliases for characters (from NameAliases.txt)
- Module:Unicode data/blocks: the list of Unicode blocks (from Blocks.txt)
- Module:Unicode data/category: data mapping characters to their General Category (from DerivedGeneralCategory.txt)
- Module:Unicode data/combining: data mapping characters to their Combining Classes (from DerivedCombiningClass.txt)
- Module:Unicode data/control: data for identifying characters that belong to the General Categories of Separator and Other (from DerivedGeneralCategory.txt)
- Module:Unicode data/derived core properties:
- Module:Unicode data/Hangul: data used to generate the names of Hangul syllables (from Jamo.txt)
- Module:Unicode data/Unihan/kCantonese/*: kCantonese pronunciation property
- Module:Unicode data/names/* (000hh, .., 0E0hh; e.g. ../names/000): names
- Module:Unicode data/scripts: data mapping characters to their Unicode script properties (from Scripts.txt).
The name data modules (Module:Unicode data/names/xxx) were compiled from UnicodeData.txt. Each one contains, at maximum, code points U+xxx000 to U+xxxFFF.
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | A | B | C | D | E | F |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 00x | U+0000– U+0FFF |
U+1000– U+1FFF |
U+2000– U+2FFF |
U+3000– U+3FFF |
U+4000– U+4FFF |
U+A000– U+AFFF |
U+D000– U+DFFF |
U+F000– U+FFFF | |||||||
| 01x | U+10000– U+10FFF |
U+11000– U+11FFF |
U+12000– U+12FFF |
U+13000– U+13FFF |
U+14000– U+14FFF |
U+16000– U+16FFF |
U+18000– U+18FFF |
U+1A000– U+1AFFF |
U+1B000– U+1BFFF |
U+1C000– U+1CFFF |
U+1D000– U+1DFFF |
U+1E000– U+1EFFF |
U+1F000– U+1FFFF | ||
| 0Ex | U+E0000– U+E0FFF |
Copyright
[edit ]The Unicode database is released by Unicode Inc. under the following terms:
Copyright © 1991-2018 Unicode, Inc. All rights reserved. Distributed under the Terms of Use in https://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 either (a) this copyright and permission notice appear with all copies of the Data Files or Software, or (b) this copyright and permission notice appear in associated Documentation.
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.
Known issues
[edit ]- Reading data like
Module:Unicode data/aliasesnot provided nor documented - Test fail:
lookup_categoryU+FFFF (<noncharacter-FFFF>) expected: Cn.
{{#invoke:Unicode data|lookup|category|0xFFFF}}→ [Nil]
See also
[edit ]- Named entities: for example, U+22C1 ⋁ N-ARY LOGICAL OR:
{{#invoke:LoadData|Numcr2namecr|0x22C1}}→ ⋁, ⋁, ⋁
Editors can experiment in this module's sandbox (edit | diff) and testcases (edit | run) pages.
Add categories to the /doc subpage. Subpages of this module.
localp={} localfloor=math.floor localfunctionerrorf(level,...) iftype(level)=="number"then returnerror(string.format(...),level+1) else-- level is actually the format string. returnerror(string.format(level,...),2) end end localfunctionbinary_range_search(codepoint,ranges) locallow,mid,high low,high=1,ranges.lengthorrequire"Module:TableTools".length(ranges) whilelow<=highdo mid=floor((low+high)/2) localrange=ranges[mid] ifcodepoint<range[1]then high=mid-1 elseifcodepoint<=range[2]then returnrange,mid else low=mid+1 end end returnnil,mid end p.binary_range_search=binary_range_search --[[ local function linear_range_search(codepoint, ranges) for i, range in ipairs(ranges) do if range[1] <= codepoint and codepoint <= range[2] then return range end end end --]] -- Load a module by indexing "loader" with the name of the module minus the -- "Module:Unicode data/" part. For instance, loader.blocks returns -- [[Module:Unicode data/blocks]]. If a module cannot be loaded, false will be -- returned. localloader=setmetatable({},{ __index=function(self,key) localsuccess,data=pcall(mw.loadData,"Module:Unicode data/"..key) ifnotsuccessthen data=false end self[key]=data returndata end }) -- For the algorithm used to generate Hangul Syllable names, -- see "Hangul Syllable Name Generation" in section 3.12 of the -- Unicode Specification: -- https://www.unicode.org/versions/Unicode11.0.0/ch03.pdf -- binary_range_search assumes these are ordered by codepoint. Do not place them in a random order! localname_hooks={ {0x00,0x1F,"<control-%04X>"},-- C0 control characters {0x7F,0x9F,"<control-%04X>"},-- DEL and C1 control characters {0x3400,0x4DBF,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension A {0x4E00,0x9FFF,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph {0xAC00,0xD7A3,function(codepoint)-- Hangul Syllables localHangul_data=loader.Hangul localsyllable_index=codepoint-0xAC00 return("HANGUL SYLLABLE %s%s%s"):format( Hangul_data.leads[floor(syllable_index/Hangul_data.final_count)], Hangul_data.vowels[floor((syllable_index%Hangul_data.final_count) /Hangul_data.trail_count)], Hangul_data.trails[syllable_index%Hangul_data.trail_count] ) end}, -- High Surrogates, High Private Use Surrogates, Low Surrogates {0xD800,0xDFFF,"<surrogate-%04X>"}, {0xE000,0xF8FF,"<private-use-%04X>"},-- Private Use -- CJK Compatibility Ideographs {0xF900,0xFA6D,"CJK COMPATIBILITY IDEOGRAPH-%04X"}, {0xFA70,0xFAD9,"CJK COMPATIBILITY IDEOGRAPH-%04X"}, {0xFE00,0xFE0F,function(codepoint)-- Variation Selectors return("VARIATION SELECTOR-%d"):format(codepoint-0xFE00+1) end}, {0x17000,0x187F7,"TANGUT IDEOGRAPH-%04X"},-- Tangut Ideograph {0x18800,0x18AFF,function(codepoint) return("TANGUT COMPONENT-%03d"):format(codepoint-0x187FF) end}, {0x18D00,0x18D08,"TANGUT IDEOGRAPH-%04X"},-- Tangut Ideograph Supplement {0x1B170,0x1B2FB,"NUSHU CHARACTER-%04X"},-- Nushu {0x20000,0x2A6DF,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension B {0x2A700,0x2B739,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension C {0x2B740,0x2B81D,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension D {0x2B820,0x2CEA1,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension E {0x2CEB0,0x2EBE0,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension F {0x2EBF0,0x2EE5D,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension I {0x2F800,0x2FA1D,"CJK COMPATIBILITY IDEOGRAPH-%04X"},-- CJK Compatibility Ideographs Supplement (Supplementary Ideographic Plane) {0x30000,0x3134A,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension G {0x31350,0x323AF,"CJK UNIFIED IDEOGRAPH-%04X"},-- CJK Ideograph Extension H {0xE0100,0xE01EF,function(codepoint)-- Variation Selectors Supplement return("VARIATION SELECTOR-%d"):format(codepoint-0xE0100+17) end}, {0xF0000,0xFFFFD,"<private-use-%04X>"},-- Plane 15 Private Use {0x100000,0x10FFFD,"<private-use-%04X>"}-- Plane 16 Private Use } name_hooks.length=#name_hooks localname_range_cache localfunctiongenerate_name(data,codepoint) iftype(data)=="string"then returndata:format(codepoint) else returndata(codepoint) end end --[[ -- Checks that the code point is a number and in range. -- Does not check whether code point is an integer. -- Not used local function check_codepoint(funcName, argIdx, val) require 'libraryUtil'.checkType(funcName, argIdx, val, 'number') if codepoint < 0 or 0x10FFFF < codepoint then errorf("Codepoint %04X out of range", codepoint) end end --]] functionp.is_noncharacter(codepoint) -- U+FDD0-U+FDEF and all code points ending in FFFE or FFFF are Unassigned -- (Cn) and specifically noncharacters: -- https://www.unicode.org/faq/private_use.html#nonchar4 return0xFDD0<=codepointand(codepoint<=0xFDEF orfloor(codepoint%0x10000)>=0xFFFE) end -- https://www.unicode.org/versions/Unicode11.0.0/ch04.pdf, section 4.8 functionp.lookup_name(codepoint) ifp.is_noncharacter(codepoint)then return("<noncharacter-%04X>"):format(codepoint) end ifname_range_cache-- Check if previously used "name hook" applies to this code point. andcodepoint>=name_range_cache[1] andcodepoint<=name_range_cache[2]then returngenerate_name(name_range_cache[3],codepoint) end localrange=binary_range_search(codepoint,name_hooks) ifrangethen name_range_cache=range returngenerate_name(range[3],codepoint) end localdata=loader[('names/%03X'):format(codepoint/0x1000)] ifdataanddata[codepoint]then returndata[codepoint] -- Unassigned (Cn) consists of noncharacters and reserved characters. -- The character has been established not to be a noncharacter, -- and if it were assigned, its name would already been retrieved, -- so it must be reserved. else return("<reserved-%04X>"):format(codepoint) end end functionp.lookup_image(codepoint) localdata=loader[('images/%03X'):format(codepoint/0x1000)] ifdatathen returndata[codepoint] end end localplanes={ [0]="Basic Multilingual Plane"; [1]="Supplementary Multilingual Plane"; [2]="Supplementary Ideographic Plane"; [3]="Tertiary Ideographic Plane"; [14]="Supplementary Special-purpose Plane"; [15]="Supplementary Private Use Area-A"; [16]="Supplementary Private Use Area-B"; } -- Load [[Module:Unicode data/blocks]] if needed and assign it to this variable. localblocks localfunctionblock_iter(blocks,i) i=i+1 localdata=blocks[i] ifdatathen -- Unpack doesn't work on tables loaded with mw.loadData. returni,data[1],data[2],data[3] end end -- An ipairs-type iterator generator for the list of blocks. functionp.enum_blocks() localblocks=loader.blocks returnblock_iter,blocks,0 end functionp.lookup_plane(codepoint) locali=floor(codepoint/0x10000) returnplanes[i]or("Plane %u"):format(i) end functionp.lookup_block(codepoint) localblocks=loader.blocks localrange=binary_range_search(codepoint,blocks) ifrangethen returnrange[3] else return"No Block" end end functionp.get_block_info(name) fori,blockinipairs(loader.blocks)do ifblock[3]==namethen returnblock end end end functionp.is_valid_pagename(pagename) localhas_nonws=false forcpinmw.ustring.gcodepoint(pagename)do if(cp==0x0023)-- # or(cp==0x005B)-- [ or(cp==0x005D)-- ] or(cp==0x007B)-- { or(cp==0x007C)-- | or(cp==0x007D)-- } or(cp==0x180E)-- MONGOLIAN VOWEL SEPARATOR or((cp>=0x2000)and(cp<=0x200A))-- spaces in General Punctuation block or(cp==0xFFFD)-- REPLACEMENT CHARACTER then returnfalse end localprintable,result=p.is_printable(cp) ifnotprintablethen returnfalse end ifresult~="space-separator"then has_nonws=true end end returnhas_nonws end localfunctionmanual_unpack(what,from) ifwhat[from+1]==nilthen returnwhat[from] end localresult={} from=fromor1 fori,iteminipairs(what)do ifi>=fromthen table.insert(result,item) end end returnunpack(result) end localfunctioncompare_ranges(range1,range2) returnrange1[1]<range2[1] end -- Creates a function to look up data in a module that contains "singles" (a -- code point-to-data map) and "ranges" (an array containing arrays that contain -- the low and high code points of a range and the data associated with that -- range). -- "loader" loads and returns the "singles" and "ranges" tables. -- "match_func" is passed the code point and either the data or the "dots", and -- generates the final result of the function. -- The varargs ("dots") describes the default data to be returned if there wasn't -- a match. -- In case the function is used more than once, "cache" saves ranges that have -- already been found to match, or a range whose data is the default if there -- was no match. localfunctionmemo_lookup(data_module_subpage,match_func,...) localdots={...} localcache={} localsingles,ranges returnfunction(codepoint) ifnotsinglesthen localdata_module=loader[data_module_subpage] singles,ranges=data_module.singles,data_module.ranges end ifsingles[codepoint]then returnmatch_func(codepoint,singles[codepoint]) end localrange=binary_range_search(codepoint,cache) ifrangethen returnmatch_func(codepoint,manual_unpack(range,3)) end localrange,index=binary_range_search(codepoint,ranges) ifrangethen table.insert(cache,range) table.sort(cache,compare_ranges) returnmatch_func(codepoint,manual_unpack(range,3)) end ifranges[index]then localdots_range ifcodepoint>ranges[index][2]then dots_range={ ranges[index][2]+1, ranges[index+1]andranges[index+1][1]-1or0x10FFFF, unpack(dots) } else-- codepoint < range[index][1] dots_range={ ranges[index-1]andranges[index-1][2]+1or0, ranges[index][1]-1, unpack(dots) } end table.sort(cache,compare_ranges) end returnmatch_func(codepoint) end end -- Get a code point's combining class value in [[Module:Unicode data/combining]], -- and return whether this value is not zero. Zero is assigned as the default -- if the combining class value is not found in this data module. -- That is, return true if character is combining, or false if it is not. -- See https://www.unicode.org/reports/tr44/#Canonical_Combining_Class_Values for -- more information. p.is_combining=memo_lookup( "combining", function(codepoint,combining_class) returncombining_classandcombining_class~=0orfalse end, 0) functionp.add_dotted_circle(str) return(mw.ustring.gsub(str,".", function(char) ifp.is_combining(mw.ustring.codepoint(char))then return'◌'..char end end)) end locallookup_control=memo_lookup( "control", function(codepoint,ccc) returncccor"assigned" end, "assigned") p.lookup_control=lookup_control functionp.is_assigned(codepoint) returnlookup_control(codepoint)~="unassigned" end functionp.is_printable(codepoint) localresult=lookup_control(codepoint) return(result=="assigned")or(result=="space-separator"),result end functionp.is_whitespace(codepoint) localresult=lookup_control(codepoint) return(result=="space-separator"),result end p.lookup_category=memo_lookup( "category", function(codepoint,category) returncategory end, "Cn") locallookup_script=memo_lookup( "scripts", function(codepoint,script_code) returnscript_codeor'Zzzz' end, "Zzzz") p.lookup_script=lookup_script functionp.get_best_script(str) -- Check type of argument, because mw.text.decode coerces numbers to strings! require"libraryUtil".checkType("get_best_script",1,str,"string") -- Convert HTML character references (including named character references, -- or character entities) to characters. str=mw.text.decode(str,true) localscripts={} forcodepointinmw.ustring.gcodepoint(str)do localscript=lookup_script(codepoint) -- Ignore "Inherited", "Undetermined", or "Uncoded" scripts. ifnot(script=="Zyyy"orscript=="Zinh"orscript=="Zzzz")then scripts[script]=true end end -- If scripts does not contain two or more keys, -- return first and only key (script code) in table. ifnotnext(scripts,next(scripts))then returnnext(scripts) end-- else return majority script, or else "Zzzz"? end functionp.is_Latin(str) require"libraryUtil".checkType("get_best_script",1,str,"string") str=mw.text.decode(str,true) -- Search for the leading bytes that introduce the UTF-8 encoding of the -- code points U+0340-U+10FFFF. If they are not found and there is at least -- one Latin-script character, the string counts as Latin, because the rest -- of the characters can only be Zyyy, Zinh, and Zzzz. -- The only scripts found below U+0370 (the first code point of the Greek -- and Coptic block) are Latn, Zyyy, Zinh, and Zzzz. -- See the codepage in the [[UTF-8]] article. ifnotstr:find"[205円-244円]"then forcodepointinmw.ustring.gcodepoint(str)do iflookup_script(codepoint)=="Latn"then returntrue end end end localLatn=false locali=0;-- indexer for use in error messages forcodepointinmw.ustring.gcodepoint(str)do i=i+1;-- bump the indexer localscript=lookup_script(codepoint) ifscript=="Latn"then Latn=true elseifnot(script=="Zyyy"orscript=="Zinh" orscript=="Zzzz")then returnfalse,i-- abandon as not Latn; identify the offending character's position end end returnLatn,(notLatnandi)ornil-- when <Latn> false, return offending charactor's position as second return value; nil else end -- Checks that a string contains only characters belonging to right-to-left -- scripts, or characters of ignorable scripts. functionp.is_rtl(str) require"libraryUtil".checkType("get_best_script",1,str,"string") str=mw.text.decode(str,true) -- Search for the leading bytes that introduce the UTF-8 encoding of the -- code points U+0580-U+10FFFF. If they are not found, the string can only -- have characters from a left-to-right script, because the first code point -- in a right-to-left script is U+0591, in the Hebrew block. ifnotstr:find"[214円-244円]"then returnfalse end localresult=false localrtl=loader.scripts.rtl forcodepointinmw.ustring.gcodepoint(str)do localscript=lookup_script(codepoint) ifrtl[script]then result=true elseifnot(script=="Zyyy"orscript=="Zinh" orscript=="Zzzz")then returnfalse end end returnresult end --[[--------------------------< I S _ R T L _ F R A M E >------------------------------------------------------ external entry from an {{#invoke:}} to determine if a string of text is rtl. Strips html and html-like tags so that those tags don't corrupt the is-rtl-is-not-rtl determination; this added for the cases where the rtl text has <br /> tags. ]] functionp.is_rtl_frame(frame) localstr=frame.args[1];-- get the string from the {{#invoke:}} frame str=str:gsub('%b<>','');-- strip any html and html-like tags returnp.is_rtl(str);-- return if whatever remains rtl; false else end localfunctionget_codepoint(args,arg) localcodepoint_string=args[arg] orerrorf(2,"Parameter %s is required",tostring(arg)) localcodepoint=tonumber(codepoint_string,16) orerrorf(2,"Parameter %s is not a code point in hexadecimal base", tostring(arg)) ifnot(0<=codepointandcodepoint<=0x10FFFF)then errorf(2,"code point in parameter %s out of range",tostring(arg)) end returncodepoint end localfunctionget_func(args,arg,prefix) localsuffix=args[arg] orerrorf(2,"Parameter %s is required",tostring(arg)) suffix=mw.text.trim(suffix) localfunc_name=prefix..suffix localfunc=p[func_name] orerrorf(2,"There is no function '%s'",func_name) returnfunc end -- This function allows any of the "lookup" functions to be invoked. The first -- parameter is the word after "lookup_"; the second parameter is the code point -- in hexadecimal base. functionp.lookup(frame) localfunc=get_func(frame.args,1,"lookup_") localcodepoint=get_codepoint(frame.args,2) localresult=func(codepoint) iffunc==p.lookup_namethen -- Prevent code point labels such as <control-0000> from being -- interpreted as HTML tags. result=result:gsub("<","<") end returnresult end functionp.is(frame) localfunc=get_func(frame.args,1,"is_") -- is_Latin and is_valid_pagename take strings. iffunc==p.is_Latinorfunc==p.is_valid_pagenameorfunc==p.is_rtlthen return(func(frame.args[2])) else-- The rest take code points. localcodepoint=get_codepoint(frame.args,2) return(func(codepoint))-- Adjust to one result. end end functionp.lookup_kCantonese(codepoint) localdata=loader[('Unihan/kCantonese/%02X'):format(floor(codepoint/0x1000))] ifdatathen returndata[codepoint] end end returnp