mugiten/unofficial_jisho_api_dart
1
0
Fork 0
mirror of https://github.com/h7x4/unofficial_jisho_api_dart.git synced 2025-09-15 09:34:57 +02:00
Code Issues Releases Activity

Rewrite some code by effective dart

Browse Source
This commit is contained in:
Oystein Kristoffer Tveit
2020-06-26 01:59:23 +02:00
parent d6509e6392
commit 093ae02c56
16 changed files with 187 additions and 185 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
lib/api.dart
View File

@@ -3,14 +3,14 @@
/// It provides a built-in http client and performs async requests to the server
/// for different types of requests.
library unofficial_jisho_api;
import './src/objects.dart';
import 'package:http/http.dart' as http;
import 'dart:convert';
import 'package:http/http.dart' as http;
import './src/phraseSearch.dart';
import './src/kanjiSearch.dart';
import './src/exampleSearch.dart';
import './src/kanjiSearch.dart';
import './src/objects.dart';
import './src/phraseScrape.dart';
import './src/phraseSearch.dart';
/// Query the official Jisho API for a word or phrase
///
@@ -53,6 +53,6 @@ Future<PhrasePageScrapeResult> scrapeForPhrase(String phrase) async {
// );
// }
throw err;
rethrow;
}
}

6
lib/parser.dart
View File

@@ -5,7 +5,7 @@
/// for providing HTML.
library unofficial_jisho_parser;
export './src/phraseSearch.dart';
export './src/kanjiSearch.dart' show uriForKanjiSearch, parseKanjiPageData;
export './src/exampleSearch.dart' show uriForExampleSearch, parseExamplePageData;
export './src/phraseScrape.dart' show uriForPhraseScrape, parsePhrasePageData;
export './src/kanjiSearch.dart' show uriForKanjiSearch, parseKanjiPageData;
export './src/phraseScrape.dart' show uriForPhraseScrape, parsePhrasePageData;
export './src/phraseSearch.dart';

28
lib/src/exampleSearch.dart
View File

@@ -1,17 +1,17 @@
import './baseURI.dart';
import './objects.dart';
import 'package:html/parser.dart';
import 'package:html/dom.dart';
final RegExp kanjiRegex = RegExp(r'[\u4e00-\u9faf\u3400-\u4dbf]');
import './baseURI.dart';
import './objects.dart';
final RegExp _kanjiRegex = RegExp(r'[\u4e00-\u9faf\u3400-\u4dbf]');
/// Provides the URI for an example search
String uriForExampleSearch(String phrase) {
return '${SCRAPE_BASE_URI}${Uri.encodeComponent(phrase)}%23sentences';
return '$SCRAPE_BASE_URI${Uri.encodeComponent(phrase)}%23sentences';
}
List<Element> getChildrenAndSymbols(Element ul) {
List<Element> _getChildrenAndSymbols(Element ul) {
final ulText = ul.text;
final ulCharArray = ulText.split('');
final ulChildren = ul.children;
@@ -25,7 +25,7 @@ List<Element> getChildrenAndSymbols(Element ul) {
symbols += ulCharArray[offsetPointer];
offsetPointer++;
}
final symbolElement = Element.html('<span>${symbols}</span>');
final symbolElement = Element.html('<span>$symbols</span>');
result.add(symbolElement);
}
offsetPointer += element.text.length;
@@ -33,15 +33,15 @@ List<Element> getChildrenAndSymbols(Element ul) {
}
if (offsetPointer + 1 != ulText.length){
final symbols = ulText.substring(offsetPointer, ulText.length-1);
final symbolElement = Element.html('<span>${symbols}</span>');
final symbolElement = Element.html('<span>$symbols</span>');
result.add(symbolElement);
}
return result;
}
ExampleResultData getKanjiAndKana(Element div) {
ExampleResultData _getKanjiAndKana(Element div) {
final ul = div.querySelector('ul');
final contents = getChildrenAndSymbols(ul);
final contents = _getChildrenAndSymbols(ul);
var kanji = '';
var kana = '';
@@ -59,7 +59,7 @@ ExampleResultData getKanjiAndKana(Element div) {
final kanaEnding = [];
for (var j = unlifted.length - 1; j > 0; j -= 1) {
final char = unlifted[j];
if (!kanjiRegex.hasMatch(char)) {
if (!_kanjiRegex.hasMatch(char)) {
kanaEnding.add(char);
} else {
break;
@@ -100,8 +100,8 @@ List<ExampleSentencePiece> getPieces(Element sentenceElement) {
return pieces;
}
ExampleResultData parseExampleDiv(Element div) {
final result = getKanjiAndKana(div);
ExampleResultData _parseExampleDiv(Element div) {
final result = _getKanjiAndKana(div);
result.english = div.querySelector('.english').text;
result.pieces = getPieces(div) ?? [];
@@ -113,7 +113,7 @@ ExampleResults parseExamplePageData(String pageHtml, String phrase) {
final document = parse(pageHtml);
final divs = document.querySelectorAll('.sentence_content');
final results = divs.map((div) => parseExampleDiv(div)).toList();
final results = divs.map((div) => _parseExampleDiv(div)).toList();
return ExampleResults(
query: phrase,

128
lib/src/kanjiSearch.dart
View File

@@ -1,49 +1,49 @@
import 'package:html_unescape/html_unescape.dart' as html_entities;
import './baseURI.dart';
import './objects.dart';
final _htmlUnescape = html_entities.HtmlUnescape();
import 'package:html_unescape/html_unescape.dart' as html_entities;
final htmlUnescape = html_entities.HtmlUnescape();
const _onyomiLocatorSymbol = 'On';
const _kunyomiLocatorSymbol = 'Kun';
const String ONYOMI_LOCATOR_SYMBOL = 'On';
const String KUNYOMI_LOCATOR_SYMBOL = 'Kun';
String removeNewlines(String str) {
String _removeNewlines(String str) {
return str.replaceAll(RegExp(r'(?:\r|\n)') , '').trim();
}
/// Provides the URI for a kanji search
String uriForKanjiSearch(String kanji) {
return '${SCRAPE_BASE_URI}${Uri.encodeComponent(kanji)}%23kanji';
return '$SCRAPE_BASE_URI${Uri.encodeComponent(kanji)}%23kanji';
}
String getUriForStrokeOrderDiagram(String kanji) {
return '${STROKE_ORDER_DIAGRAM_BASE_URI}${kanji.codeUnitAt(0)}_frames.png';
String _getUriForStrokeOrderDiagram(String kanji) {
return '$STROKE_ORDER_DIAGRAM_BASE_URI${kanji.codeUnitAt(0)}_frames.png';
}
bool containsKanjiGlyph(String pageHtml, String kanji) {
final kanjiGlyphToken = '<h1 class="character" data-area-name="print" lang="ja">${kanji}</h1>';
bool _containsKanjiGlyph(String pageHtml, String kanji) {
final kanjiGlyphToken = '<h1 class="character" data-area-name="print" lang="ja">$kanji</h1>';
return pageHtml.contains(kanjiGlyphToken);
}
String getStringBetweenIndicies(String data, int startIndex, int endIndex) {
String _getStringBetweenIndicies(String data, int startIndex, int endIndex) {
final result = data.substring(startIndex, endIndex);
return removeNewlines(result).trim();
return _removeNewlines(result).trim();
}
String getStringBetweenStrings(String data, String startString, String endString) {
String _getStringBetweenStrings(String data, String startString, String endString) {
final regex = RegExp('${RegExp.escape(startString)}(.*?)${RegExp.escape(endString)}', dotAll: true);
final match = regex.allMatches(data).toList();
return match.isNotEmpty ? match[0].group(1).toString() : null;
}
int getIntBetweenStrings(String pageHtml, String startString, String endString) {
final stringBetweenStrings = getStringBetweenStrings(pageHtml, startString, endString);
int _getIntBetweenStrings(String pageHtml, String startString, String endString) {
final stringBetweenStrings = _getStringBetweenStrings(pageHtml, startString, endString);
return int.parse(stringBetweenStrings);
}
List<String> getAllGlobalGroupMatches(String str, RegExp regex) {
List<String> _getAllGlobalGroupMatches(String str, RegExp regex) {
var regexResults = regex.allMatches(str).toList();
List<String> results = [];
for (var match in regexResults) {
@@ -53,59 +53,59 @@ List<String> getAllGlobalGroupMatches(String str, RegExp regex) {
return results;
}
List<String> parseAnchorsToArray(String str) {
List<String> _parseAnchorsToArray(String str) {
final regex = RegExp(r'<a href=".*?">(.*?)<\/a>');
return getAllGlobalGroupMatches(str, regex);
return _getAllGlobalGroupMatches(str, regex);
}
List<String> getYomi(String pageHtml, String yomiLocatorSymbol) {
final yomiSection = getStringBetweenStrings(pageHtml, '<dt>${yomiLocatorSymbol}:</dt>', '</dl>');
return parseAnchorsToArray(yomiSection ?? '');
List<String> _getYomi(String pageHtml, String yomiLocatorSymbol) {
final yomiSection = _getStringBetweenStrings(pageHtml, '<dt>$yomiLocatorSymbol:</dt>', '</dl>');
return _parseAnchorsToArray(yomiSection ?? '');
}
List<String> getKunyomi(String pageHtml) {
return getYomi(pageHtml, KUNYOMI_LOCATOR_SYMBOL);
List<String> _getKunyomi(String pageHtml) {
return _getYomi(pageHtml, _kunyomiLocatorSymbol);
}
List<String> getOnyomi(String pageHtml) {
return getYomi(pageHtml, ONYOMI_LOCATOR_SYMBOL);
List<String> _getOnyomi(String pageHtml) {
return _getYomi(pageHtml, _onyomiLocatorSymbol);
}
List<YomiExample> getYomiExamples(String pageHtml, String yomiLocatorSymbol) {
final locatorString = '<h2>${yomiLocatorSymbol} reading compounds</h2>';
final exampleSection = getStringBetweenStrings(pageHtml, locatorString, '</ul>');
List<YomiExample> _getYomiExamples(String pageHtml, String yomiLocatorSymbol) {
final locatorString = '<h2>$yomiLocatorSymbol reading compounds</h2>';
final exampleSection = _getStringBetweenStrings(pageHtml, locatorString, '</ul>');
if (exampleSection==null) {
return null;
}
final regex = RegExp(r'<li>(.*?)<\/li>', dotAll: true);
final regexResults = getAllGlobalGroupMatches(exampleSection, regex).map((s) => s.trim());
final regexResults = _getAllGlobalGroupMatches(exampleSection, regex).map((s) => s.trim());
final examples = regexResults.map((regexResult) {
final examplesLines = regexResult.split('\n').map((s) => s.trim()).toList();
return YomiExample(
example: examplesLines[0],
reading: examplesLines[1].replaceAll('【', '').replaceAll('】', ''),
meaning: htmlUnescape.convert(examplesLines[2]),
meaning: _htmlUnescape.convert(examplesLines[2]),
);
});
return examples.toList();
}
List<YomiExample> getOnyomiExamples(String pageHtml) {
return getYomiExamples(pageHtml, ONYOMI_LOCATOR_SYMBOL);
List<YomiExample> _getOnyomiExamples(String pageHtml) {
return _getYomiExamples(pageHtml, _onyomiLocatorSymbol);
}
List<YomiExample> getKunyomiExamples(String pageHtml) {
return getYomiExamples(pageHtml, KUNYOMI_LOCATOR_SYMBOL);
List<YomiExample> _getKunyomiExamples(String pageHtml) {
return _getYomiExamples(pageHtml, _kunyomiLocatorSymbol);
}
Radical getRadical(String pageHtml) {
Radical _getRadical(String pageHtml) {
const radicalMeaningStartString = '<span class="radical_meaning">';
const radicalMeaningEndString = '</span>';
var radicalMeaning = getStringBetweenStrings(
var radicalMeaning = _getStringBetweenStrings(
pageHtml,
radicalMeaningStartString,
radicalMeaningEndString,
@@ -123,7 +123,7 @@ Radical getRadical(String pageHtml) {
const radicalSymbolEndString = '</span>';
final radicalSymbolEndIndex = pageHtml.indexOf(radicalSymbolEndString, radicalSymbolStartIndex);
final radicalSymbolsString = getStringBetweenIndicies(
final radicalSymbolsString = _getStringBetweenIndicies(
pageHtml,
radicalSymbolStartIndex,
radicalSymbolEndIndex,
@@ -153,64 +153,64 @@ Radical getRadical(String pageHtml) {
return null;
}
List<String> getParts(String pageHtml) {
List<String> _getParts(String pageHtml) {
const partsSectionStartString = '<dt>Parts:</dt>';
const partsSectionEndString = '</dl>';
final partsSection = getStringBetweenStrings(
final partsSection = _getStringBetweenStrings(
pageHtml,
partsSectionStartString,
partsSectionEndString,
);
var result = parseAnchorsToArray(partsSection);
var result = _parseAnchorsToArray(partsSection);
result.sort();
return (result);
}
String getSvgUri(String pageHtml) {
String _getSvgUri(String pageHtml) {
var svgRegex = RegExp('\/\/.*?.cloudfront.net\/.*?.svg');
final regexResult = svgRegex.firstMatch(pageHtml).group(0).toString();
return regexResult.isNotEmpty ? 'https:${regexResult}' : null;
return regexResult.isNotEmpty ? 'https:$regexResult' : null;
}
String getGifUri(String kanji) {
String _getGifUri(String kanji) {
final unicodeString = kanji.codeUnitAt(0).toRadixString(16);
final fileName = '${unicodeString}.gif';
final animationUri = 'https://raw.githubusercontent.com/mistval/kanji_images/master/gifs/${fileName}';
final fileName = '$unicodeString.gif';
final animationUri = 'https://raw.githubusercontent.com/mistval/kanji_images/master/gifs/$fileName';
return animationUri;
}
int getNewspaperFrequencyRank(String pageHtml) {
final frequencySection = getStringBetweenStrings(pageHtml, '<div class="frequency">', '</div>');
return (frequencySection != null) ? int.parse(getStringBetweenStrings(frequencySection, '<strong>', '</strong>')) : null;
int _getNewspaperFrequencyRank(String pageHtml) {
final frequencySection = _getStringBetweenStrings(pageHtml, '<div class="frequency">', '</div>');
return (frequencySection != null) ? int.parse(_getStringBetweenStrings(frequencySection, '<strong>', '</strong>')) : null;
}
/// Parses a jisho kanji search page to an object
KanjiResult parseKanjiPageData(String pageHtml, String kanji) {
final result = KanjiResult();
result.query = kanji;
result.found = containsKanjiGlyph(pageHtml, kanji);
result.found = _containsKanjiGlyph(pageHtml, kanji);
if (result.found==false) {
return result;
}
result.taughtIn = getStringBetweenStrings(pageHtml, 'taught in <strong>', '</strong>');
result.jlptLevel = getStringBetweenStrings(pageHtml, 'JLPT level <strong>', '</strong>');
result.newspaperFrequencyRank = getNewspaperFrequencyRank(pageHtml);
result.strokeCount = getIntBetweenStrings(pageHtml, '<strong>', '</strong> strokes');
result.meaning = htmlUnescape.convert(removeNewlines(getStringBetweenStrings(pageHtml, '<div class="kanji-details__main-meanings">', '</div>')).trim());
result.kunyomi = getKunyomi(pageHtml) ?? [];
result.onyomi = getOnyomi(pageHtml) ?? [];
result.onyomiExamples = getOnyomiExamples(pageHtml) ?? [];
result.kunyomiExamples = getKunyomiExamples(pageHtml) ?? [];
result.radical = getRadical(pageHtml);
result.parts = getParts(pageHtml) ?? [];
result.strokeOrderDiagramUri = getUriForStrokeOrderDiagram(kanji);
result.strokeOrderSvgUri = getSvgUri(pageHtml);
result.strokeOrderGifUri = getGifUri(kanji);
result.taughtIn = _getStringBetweenStrings(pageHtml, 'taught in <strong>', '</strong>');
result.jlptLevel = _getStringBetweenStrings(pageHtml, 'JLPT level <strong>', '</strong>');
result.newspaperFrequencyRank = _getNewspaperFrequencyRank(pageHtml);
result.strokeCount = _getIntBetweenStrings(pageHtml, '<strong>', '</strong> strokes');
result.meaning = _htmlUnescape.convert(_removeNewlines(_getStringBetweenStrings(pageHtml, '<div class="kanji-details__main-meanings">', '</div>')).trim());
result.kunyomi = _getKunyomi(pageHtml) ?? [];
result.onyomi = _getOnyomi(pageHtml) ?? [];
result.onyomiExamples = _getOnyomiExamples(pageHtml) ?? [];
result.kunyomiExamples = _getKunyomiExamples(pageHtml) ?? [];
result.radical = _getRadical(pageHtml);
result.parts = _getParts(pageHtml) ?? [];
result.strokeOrderDiagramUri = _getUriForStrokeOrderDiagram(kanji);
result.strokeOrderSvgUri = _getSvgUri(pageHtml);
result.strokeOrderGifUri = _getGifUri(kanji);
result.uri = uriForKanjiSearch(kanji);
return result;
}

46
lib/src/phraseScrape.dart
View File

@@ -1,10 +1,10 @@
import './objects.dart';
import './exampleSearch.dart';
import 'package:html/parser.dart';
import 'package:html/dom.dart';
List<String> getTags(Document document) {
import './exampleSearch.dart' show getPieces;
import './objects.dart';
List<String> _getTags(Document document) {
final List<String> tags = [];
final tagElements = document.querySelectorAll('.concept_light-tag');
@@ -16,21 +16,21 @@ List<String> getTags(Document document) {
return tags;
}
List<String> getMostRecentWordTypes(Element child) {
List<String> _getMostRecentWordTypes(Element child) {
return child.text.split(',').map((s) => s.trim().toLowerCase()).toList();
}
List<KanjiKanaPair> getOtherForms(Element child) {
List<KanjiKanaPair> _getOtherForms(Element child) {
return child.text.split('、')
.map((s) => s.replaceAll('【', '').replaceAll('】', '').split(' '))
.map((a) => (KanjiKanaPair( kanji: a[0], kana: (a.length == 2) ? a[1] : null ))).toList();
}
List<String> getNotes(Element child) => child.text.split('\n');
List<String> _getNotes(Element child) => child.text.split('\n');
String getMeaning(Element child) => child.querySelector('.meaning-meaning').text;
String _getMeaning(Element child) => child.querySelector('.meaning-meaning').text;
String getMeaningAbstract(Element child) {
String _getMeaningAbstract(Element child) {
final meaningAbstract = child.querySelector('.meaning-abstract');
if (meaningAbstract == null) return null;
@@ -41,13 +41,13 @@ String getMeaningAbstract(Element child) {
return child.querySelector('.meaning-abstract')?.text;
}
List<String> getSupplemental(Element child) {
List<String> _getSupplemental(Element child) {
final supplemental = child.querySelector('.supplemental_info');
if (supplemental == null) return [];
return supplemental.text.split(',').map((s) => s.trim()).toList();
}
List<String> getSeeAlsoTerms(List<String> supplemental) {
List<String> _getSeeAlsoTerms(List<String> supplemental) {
if (supplemental == null) return [];
final List<String> seeAlsoTerms = [];
@@ -61,7 +61,7 @@ List<String> getSeeAlsoTerms(List<String> supplemental) {
return seeAlsoTerms;
}
List<PhraseScrapeSentence> getSentences(Element child) {
List<PhraseScrapeSentence> _getSentences(Element child) {
final sentenceElements = child.querySelector('.sentences')?.querySelectorAll('.sentence');
if (sentenceElements == null) return [];
@@ -91,7 +91,7 @@ List<PhraseScrapeSentence> getSentences(Element child) {
return sentences;
}
PhrasePageScrapeResult getMeaningsOtherFormsAndNotes(Document document) {
PhrasePageScrapeResult _getMeaningsOtherFormsAndNotes(Document document) {
final returnValues = PhrasePageScrapeResult( otherForms: [], notes: [] );
final meaningsWrapper = document.querySelector('.meanings-wrapper');
@@ -106,20 +106,20 @@ PhrasePageScrapeResult getMeaningsOtherFormsAndNotes(Document document) {
final child = meaningsChildren[meaningIndex];
if (child.className.contains('meaning-tags')) {
mostRecentWordTypes = getMostRecentWordTypes(child);
mostRecentWordTypes = _getMostRecentWordTypes(child);
} else if (mostRecentWordTypes[0] == 'other forms') {
returnValues.otherForms = getOtherForms(child);
returnValues.otherForms = _getOtherForms(child);
} else if (mostRecentWordTypes[0] == 'notes') {
returnValues.notes = getNotes(child);
returnValues.notes = _getNotes(child);
} else {
final meaning = getMeaning(child);
final meaningAbstract = getMeaningAbstract(child);
final supplemental = getSupplemental(child);
final seeAlsoTerms = getSeeAlsoTerms(supplemental);
final sentences = getSentences(child);
final meaning = _getMeaning(child);
final meaningAbstract = _getMeaningAbstract(child);
final supplemental = _getSupplemental(child);
final seeAlsoTerms = _getSeeAlsoTerms(supplemental);
final sentences = _getSentences(child);
meanings.add(PhraseScrapeMeaning(
seeAlsoTerms: seeAlsoTerms ?? [],
@@ -145,12 +145,12 @@ String uriForPhraseScrape(String searchTerm) {
/// Parses a jisho word search page to an object
PhrasePageScrapeResult parsePhrasePageData(String pageHtml, String query) {
final document = parse(pageHtml);
final result = getMeaningsOtherFormsAndNotes(document);
final result = _getMeaningsOtherFormsAndNotes(document);
result.query = query;
if (!result.found) return result;
result.uri = uriForPhraseScrape(query);
result.tags = getTags(document);
result.tags = _getTags(document);
return result;
}

2
lib/src/phraseSearch.dart
View File

@@ -3,5 +3,5 @@ import './baseURI.dart';
/// Provides the URI for a phrase search
String uriForPhraseSearch(String phrase) {
return '${JISHO_API}?keyword=${Uri.encodeComponent(phrase)}';
return '$JISHO_API?keyword=${Uri.encodeComponent(phrase)}';
}