summaryrefslogtreecommitdiff
path: root/ext/js/language
diff options
context:
space:
mode:
authortoasted-nutbread <toasted-nutbread@users.noreply.github.com>2021-10-14 21:26:53 -0400
committerGitHub <noreply@github.com>2021-10-14 21:26:53 -0400
commit75aabd983da29023b8423bd44d565202aad6b664 (patch)
tree754fbe5457747cd72fcf13767fc3176fc0d8f280 /ext/js/language
parent11f7591a7f5fcbfc3a3e631eaac0addb228c988a (diff)
String frequency support (#1989)
* Restore support for string frequency values * Add support for {value, displayValue} frequencies * Update test data * Improve number parsing of string frequencies * Improve reading detection * Expose a displayValue property for frequency information * Update docs * Expose displayValue to Anki note data * Fix translator * Update display generation * Update test data * Update counts
Diffstat (limited to 'ext/js/language')
-rw-r--r--ext/js/language/sandbox/dictionary-data-util.js14
-rw-r--r--ext/js/language/translator.js61
2 files changed, 52 insertions, 23 deletions
diff --git a/ext/js/language/sandbox/dictionary-data-util.js b/ext/js/language/sandbox/dictionary-data-util.js
index 68b15c48..83d94b9b 100644
--- a/ext/js/language/sandbox/dictionary-data-util.js
+++ b/ext/js/language/sandbox/dictionary-data-util.js
@@ -48,7 +48,7 @@ class DictionaryDataUtil {
const {headwords, frequencies} = dictionaryEntry;
const map1 = new Map();
- for (const {headwordIndex, dictionary, hasReading, frequency} of frequencies) {
+ for (const {headwordIndex, dictionary, hasReading, frequency, displayValue} of frequencies) {
const {term, reading} = headwords[headwordIndex];
let map2 = map1.get(dictionary);
@@ -61,18 +61,18 @@ class DictionaryDataUtil {
const key = this._createMapKey([term, readingKey]);
let frequencyData = map2.get(key);
if (typeof frequencyData === 'undefined') {
- frequencyData = {term, reading: readingKey, values: new Set()};
+ frequencyData = {term, reading: readingKey, values: new Map()};
map2.set(key, frequencyData);
}
- frequencyData.values.add(frequency);
+ frequencyData.values.set(this._createMapKey([frequency, displayValue]), {frequency, displayValue});
}
return this._createFrequencyGroupsFromMap(map1);
}
static groupKanjiFrequencies(frequencies) {
const map1 = new Map();
- for (const {dictionary, character, frequency} of frequencies) {
+ for (const {dictionary, character, frequency, displayValue} of frequencies) {
let map2 = map1.get(dictionary);
if (typeof map2 === 'undefined') {
map2 = new Map();
@@ -81,11 +81,11 @@ class DictionaryDataUtil {
let frequencyData = map2.get(character);
if (typeof frequencyData === 'undefined') {
- frequencyData = {character, values: new Set()};
+ frequencyData = {character, values: new Map()};
map2.set(character, frequencyData);
}
- frequencyData.values.add(frequency);
+ frequencyData.values.set(this._createMapKey([frequency, displayValue]), {frequency, displayValue});
}
return this._createFrequencyGroupsFromMap(map1);
}
@@ -222,7 +222,7 @@ class DictionaryDataUtil {
for (const [dictionary, map2] of map.entries()) {
const frequencies = [];
for (const frequencyData of map2.values()) {
- frequencyData.values = [...frequencyData.values];
+ frequencyData.values = [...frequencyData.values.values()];
frequencies.push(frequencyData);
}
results.push({dictionary, frequencies});
diff --git a/ext/js/language/translator.js b/ext/js/language/translator.js
index 056ff3a7..28e1cfcc 100644
--- a/ext/js/language/translator.js
+++ b/ext/js/language/translator.js
@@ -36,6 +36,7 @@ class Translator {
this._deinflector = null;
this._tagCache = new Map();
this._stringComparer = new Intl.Collator('en-US'); // Invariant locale
+ this._numberRegex = /[+-]?(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?/;
}
/**
@@ -853,12 +854,15 @@ class Translator {
case 'freq':
{
let frequency = data;
- const hasReading = (data !== null && typeof data === 'object');
+ const hasReading = (data !== null && typeof data === 'object' && typeof data.reading === 'string');
if (hasReading) {
if (data.reading !== reading) { continue; }
frequency = data.frequency;
}
for (const {frequencies, headwordIndex} of targets) {
+ let displayValue;
+ let displayValueParsed;
+ ({frequency, displayValue, displayValueParsed} = this._getFrequencyInfo(frequency));
frequencies.push(this._createTermFrequency(
frequencies.length,
headwordIndex,
@@ -866,7 +870,9 @@ class Translator {
dictionaryIndex,
dictionaryPriority,
hasReading,
- this._convertFrequency(frequency)
+ frequency,
+ displayValue,
+ displayValueParsed
));
}
}
@@ -914,13 +920,16 @@ class Translator {
case 'freq':
{
const {frequencies} = dictionaryEntries[index];
+ const {frequency, displayValue, displayValueParsed} = this._getFrequencyInfo(data);
frequencies.push(this._createKanjiFrequency(
frequencies.length,
dictionary,
dictionaryIndex,
dictionaryPriority,
character,
- this._convertFrequency(data)
+ frequency,
+ displayValue,
+ displayValueParsed
));
}
break;
@@ -971,16 +980,36 @@ class Translator {
});
}
- _convertFrequency(value) {
- switch (typeof value) {
- case 'number':
- return value;
- case 'string':
- value = Number.parseFloat(value);
- return Number.isFinite(value) ? value : 0;
- default:
- return 0;
+ _convertStringToNumber(value) {
+ const match = this._numberRegex.exec(value);
+ if (match === null) { return 0; }
+ value = Number.parseFloat(match[0]);
+ return Number.isFinite(value) ? value : 0;
+ }
+
+ _getFrequencyInfo(frequency) {
+ let displayValue = null;
+ let displayValueParsed = false;
+ if (typeof frequency === 'object' && frequency !== null) {
+ ({value: frequency, displayValue} = frequency);
+ if (typeof frequency !== 'number') { frequency = 0; }
+ if (typeof displayValue !== 'string') { displayValue = null; }
+ } else {
+ switch (typeof frequency) {
+ case 'number':
+ // No change
+ break;
+ case 'string':
+ displayValue = frequency;
+ displayValueParsed = true;
+ frequency = this._convertStringToNumber(frequency);
+ break;
+ default:
+ frequency = 0;
+ break;
+ }
}
+ return {frequency, displayValue, displayValueParsed};
}
// Helpers
@@ -1048,8 +1077,8 @@ class Translator {
};
}
- _createKanjiFrequency(index, dictionary, dictionaryIndex, dictionaryPriority, character, frequency) {
- return {index, dictionary, dictionaryIndex, dictionaryPriority, character, frequency};
+ _createKanjiFrequency(index, dictionary, dictionaryIndex, dictionaryPriority, character, frequency, displayValue, displayValueParsed) {
+ return {index, dictionary, dictionaryIndex, dictionaryPriority, character, frequency, displayValue, displayValueParsed};
}
_createKanjiDictionaryEntry(character, dictionary, onyomi, kunyomi, tags, stats, definitions) {
@@ -1114,8 +1143,8 @@ class Translator {
return {index, headwordIndex, dictionary, dictionaryIndex, dictionaryPriority, pitches};
}
- _createTermFrequency(index, headwordIndex, dictionary, dictionaryIndex, dictionaryPriority, hasReading, frequency) {
- return {index, headwordIndex, dictionary, dictionaryIndex, dictionaryPriority, hasReading, frequency};
+ _createTermFrequency(index, headwordIndex, dictionary, dictionaryIndex, dictionaryPriority, hasReading, frequency, displayValue, displayValueParsed) {
+ return {index, headwordIndex, dictionary, dictionaryIndex, dictionaryPriority, hasReading, frequency, displayValue, displayValueParsed};
}
_createTermDictionaryEntry(isPrimary, inflections, score, dictionaryIndex, dictionaryPriority, sourceTermExactMatchCount, maxTransformedTextLength, headwords, definitions) {