Ignore diacritics in autocomplete

Works for:
- Choice
- Choice List
- Reference
- Reference List

Co-Authored-By: Louis Delbosc <louis.delbosc.prestataire@anct.gouv.fr>
This commit is contained in:
Ronan Amicel 2022-08-09 15:43:44 +02:00
parent 103c795aa2
commit 2a05d04e35
6 changed files with 22 additions and 11 deletions

View File

@ -7,7 +7,7 @@
* "lush" would only match the "L" in "Lavender". * "lush" would only match the "L" in "Lavender".
*/ */
import {localeCompare, nativeCompare, sortedIndex} from 'app/common/gutil'; import {localeCompare, nativeCompare, removeDiacritics, sortedIndex} from 'app/common/gutil';
import {DomContents} from 'grainjs'; import {DomContents} from 'grainjs';
import escapeRegExp = require("lodash/escapeRegExp"); import escapeRegExp = require("lodash/escapeRegExp");
@ -17,6 +17,12 @@ export interface ACItem {
cleanText: string; cleanText: string;
} }
// Returns a normalized, trimmed, lowercase version of a string, so that autocomplete is case-
// and accent-insensitive.
export function cleanText(text: string): string {
return removeDiacritics(text).trim().toLowerCase();
}
// Regexp used to split text into words; includes nearly all punctuation. This means that // Regexp used to split text into words; includes nearly all punctuation. This means that
// "foo-bar" may be searched by "bar", but it's impossible to search for punctuation itself (e.g. // "foo-bar" may be searched by "bar", but it's impossible to search for punctuation itself (e.g.
// "a-b" and "a+b" are not distinguished). (It's easy to exclude unicode punctuation too if the // "a-b" and "a+b" are not distinguished). (It's easy to exclude unicode punctuation too if the
@ -91,7 +97,7 @@ export class ACIndexImpl<Item extends ACItem> implements ACIndex<Item> {
// The main search function. SearchText will be cleaned (trimmed and lowercased) at the start. // The main search function. SearchText will be cleaned (trimmed and lowercased) at the start.
// Empty search text returns the first N items in the search universe. // Empty search text returns the first N items in the search universe.
public search(searchText: string): ACResults<Item> { public search(searchText: string): ACResults<Item> {
const cleanedSearchText = searchText.trim().toLowerCase(); const cleanedSearchText = cleanText(searchText);
const searchWords = cleanedSearchText.split(wordSepRegexp).filter(w => w); const searchWords = cleanedSearchText.split(wordSepRegexp).filter(w => w);
// Maps item index in _allItems to its score. // Maps item index in _allItems to its score.

View File

@ -8,7 +8,7 @@
* *
* It is currently used for auto-complete in the ReferenceEditor and ReferenceListEditor widgets. * It is currently used for auto-complete in the ReferenceEditor and ReferenceListEditor widgets.
*/ */
import {ACIndex, ACIndexImpl} from 'app/client/lib/ACIndex'; import {ACIndex, ACIndexImpl, cleanText as clean} from 'app/client/lib/ACIndex';
import {ColumnCache} from 'app/client/models/ColumnCache'; import {ColumnCache} from 'app/client/models/ColumnCache';
import {UserError} from 'app/client/models/errors'; import {UserError} from 'app/client/models/errors';
import {TableData} from 'app/client/models/TableData'; import {TableData} from 'app/client/models/TableData';
@ -45,7 +45,7 @@ export class ColumnACIndexes {
const items: ICellItem[] = valColumn.map((val, i) => { const items: ICellItem[] = valColumn.map((val, i) => {
const rowId = rowIds[i]; const rowId = rowIds[i];
const text = formatter.formatAny(val); const text = formatter.formatAny(val);
const cleanText = text.trim().toLowerCase(); const cleanText = clean(text);
return {rowId, text, cleanText}; return {rowId, text, cleanText};
}); });
items.sort(itemCompare); items.sort(itemCompare);

View File

@ -1,5 +1,5 @@
import {createGroup} from 'app/client/components/commands'; import {createGroup} from 'app/client/components/commands';
import {ACIndexImpl, ACItem, ACResults, buildHighlightedDom, HighlightFunc} from 'app/client/lib/ACIndex'; import {ACIndexImpl, ACItem, ACResults, buildHighlightedDom, cleanText as clean, HighlightFunc} from 'app/client/lib/ACIndex';
import {IAutocompleteOptions} from 'app/client/lib/autocomplete'; import {IAutocompleteOptions} from 'app/client/lib/autocomplete';
import {IToken, TokenField, tokenFieldStyles} from 'app/client/lib/TokenField'; import {IToken, TokenField, tokenFieldStyles} from 'app/client/lib/TokenField';
import {colors, testId} from 'app/client/ui2018/cssVars'; import {colors, testId} from 'app/client/ui2018/cssVars';
@ -16,7 +16,7 @@ import {choiceToken, cssChoiceACItem, cssChoiceToken} from 'app/client/widgets/C
import {icon} from 'app/client/ui2018/icons'; import {icon} from 'app/client/ui2018/icons';
export class ChoiceItem implements ACItem, IToken { export class ChoiceItem implements ACItem, IToken {
public cleanText: string = this.label.toLowerCase().trim(); public cleanText: string = clean(this.label);
constructor( constructor(
public label: string, public label: string,
public isInvalid: boolean, // If set, this token is not one of the valid choices. public isInvalid: boolean, // If set, this token is not one of the valid choices.

View File

@ -1,4 +1,4 @@
import { ACResults, buildHighlightedDom, HighlightFunc } from 'app/client/lib/ACIndex'; import { ACResults, buildHighlightedDom, cleanText as clean, HighlightFunc } from 'app/client/lib/ACIndex';
import { Autocomplete } from 'app/client/lib/autocomplete'; import { Autocomplete } from 'app/client/lib/autocomplete';
import { ICellItem } from 'app/client/models/ColumnACIndexes'; import { ICellItem } from 'app/client/models/ColumnACIndexes';
import { reportError } from 'app/client/models/errors'; import { reportError } from 'app/client/models/errors';
@ -115,7 +115,7 @@ export class ReferenceEditor extends NTextEditor {
this._showAddNew = false; this._showAddNew = false;
if (!this._enableAddNew || !text) { return result; } if (!this._enableAddNew || !text) { return result; }
const cleanText = text.trim().toLowerCase(); const cleanText = clean(text);
if (result.items.find((item) => item.cleanText === cleanText)) { if (result.items.find((item) => item.cleanText === cleanText)) {
return result; return result;
} }

View File

@ -1,5 +1,5 @@
import { createGroup } from 'app/client/components/commands'; import { createGroup } from 'app/client/components/commands';
import { ACItem, ACResults, HighlightFunc } from 'app/client/lib/ACIndex'; import { ACItem, ACResults, cleanText as clean, HighlightFunc } from 'app/client/lib/ACIndex';
import { IAutocompleteOptions } from 'app/client/lib/autocomplete'; import { IAutocompleteOptions } from 'app/client/lib/autocomplete';
import { IToken, TokenField, tokenFieldStyles } from 'app/client/lib/TokenField'; import { IToken, TokenField, tokenFieldStyles } from 'app/client/lib/TokenField';
import { reportError } from 'app/client/models/errors'; import { reportError } from 'app/client/models/errors';
@ -26,7 +26,7 @@ class ReferenceItem implements IToken, ACItem {
* similar to getItemText() from IAutocompleteOptions. * similar to getItemText() from IAutocompleteOptions.
*/ */
public label: string = typeof this.rowId === 'number' ? String(this.rowId) : this.text; public label: string = typeof this.rowId === 'number' ? String(this.rowId) : this.text;
public cleanText: string = this.text.trim().toLowerCase(); public cleanText: string = clean(this.text);
constructor( constructor(
public text: string, public text: string,
@ -264,7 +264,7 @@ export class ReferenceListEditor extends NewBaseEditor {
this._showAddNew = false; this._showAddNew = false;
if (!this._enableAddNew || !text) { return result; } if (!this._enableAddNew || !text) { return result; }
const cleanText = text.trim().toLowerCase(); const cleanText = clean(text);
if (result.items.find((item) => item.cleanText === cleanText)) { if (result.items.find((item) => item.cleanText === cleanText)) {
return result; return result;
} }

View File

@ -55,6 +55,11 @@ export function capitalizeFirstWord(str: string): string {
return str.replace(/\b[a-z]/i, c => c.toUpperCase()); return str.replace(/\b[a-z]/i, c => c.toUpperCase());
} }
// Remove diacritics (accents and other signs).
export function removeDiacritics(text: string): string {
return text.normalize("NFKD").replace(/[\u0300-\u036f]/g, "")
}
// Returns whether the string n represents a valid number. // Returns whether the string n represents a valid number.
// http://stackoverflow.com/questions/18082/validate-numbers-in-javascript-isnumeric // http://stackoverflow.com/questions/18082/validate-numbers-in-javascript-isnumeric
export function isNumber(n: string): boolean { export function isNumber(n: string): boolean {