landvex: Fixar och tester klara för alla komponenter

- Datafabrik: Dockerfile fix, agentorkestrering fungerar
- Vision: Identify-modell, FAISS, OCR alla testade
- API: Alla 7 integrationstester passerade
- Upplösare: Entitetsupplösning verifierad
This commit is contained in:
Bernt
2026-07-05 06:41:32 +00:00
parent f4f853d94b
commit aee0f09db8
19583 changed files with 1450867 additions and 1153 deletions
@@ -0,0 +1,25 @@
name: Unit tests
on:
push:
branches: [ master ]
pull_request:
branches: [ master ]
jobs:
build:
runs-on: ubuntu-latest
strategy:
matrix:
node-version: [14.x, 15.x, 16.x, 17.x, 18.x, 19.x, 20.x]
steps:
- uses: actions/checkout@v3
- name: Use Node ${{ matrix.node-version }}
uses: actions/setup-node@v3
with:
node-version: ${{ matrix.node-version }}
- run: npm install
- run: npm test
+22
View File
@@ -0,0 +1,22 @@
The MIT License (MIT)
Copyright (c) 2015 Marin Atanasov
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS 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. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
+71
View File
@@ -0,0 +1,71 @@
# remove-accents
Removes the accents from a string, converting them to their corresponding non-accented ASCII characters.
```
npm install remove-accents
```
[![Unit tests](https://github.com/tyxla/remove-accents/actions/workflows/unit-tests.yml/badge.svg)](https://github.com/tyxla/remove-accents/actions/workflows/unit-tests.yml)
## About
An easy to use solution for converting all accented characters to their corresponding non-accented ASCII characters.
## Syntax
``` js
import removeAccents from 'remove-accents';
removeAccents(inputString)
```
Alternatively, you could use the CommonJS syntax to import it:
``` js
const removeAccents = require('remove-accents');
```
#### inputString
The string that you wish to remove accents from.
## Usage
Call `removeAccents()` by passing the string you wish to remove accents from, and you will get the non-accented string as result.
``` js
const input = 'ÀÁÂÃÄÅ';
const output = removeAccents(input);
console.log(output); // AAAAAA
```
## Methods
The exported function also has helper methods.
#### has
Determine if a string has any accented characters.
``` js
import removeAccents from 'remove-accents';
console.log(removeAccents.has('ÀÁÂÃÄÅ')); // true
console.log(removeAccents.has('ABC')); // false
```
#### remove
Alias of `removeAccents`.
``` js
import removeAccents from 'remove-accents';
console.log(removeAccents.remove('ÀÁÂÃÄÅ')); // AAAAAA
```
## License
MIT
+8
View File
@@ -0,0 +1,8 @@
interface RemoveAccents {
(part: string): string;
remove(part: string): string;
has(part: string): boolean;
}
declare var dm: RemoveAccents;
export = dm;
+481
View File
@@ -0,0 +1,481 @@
var characterMap = {
"À": "A",
"Á": "A",
"Â": "A",
"Ã": "A",
"Ä": "A",
"Å": "A",
"Ấ": "A",
"Ắ": "A",
"Ẳ": "A",
"Ẵ": "A",
"Ặ": "A",
"Æ": "AE",
"Ầ": "A",
"Ằ": "A",
"Ȃ": "A",
"Ả": "A",
"Ạ": "A",
"Ẩ": "A",
"Ẫ": "A",
"Ậ": "A",
"Ç": "C",
"Ḉ": "C",
"È": "E",
"É": "E",
"Ê": "E",
"Ë": "E",
"Ế": "E",
"Ḗ": "E",
"Ề": "E",
"Ḕ": "E",
"Ḝ": "E",
"Ȇ": "E",
"Ẻ": "E",
"Ẽ": "E",
"Ẹ": "E",
"Ể": "E",
"Ễ": "E",
"Ệ": "E",
"Ì": "I",
"Í": "I",
"Î": "I",
"Ï": "I",
"Ḯ": "I",
"Ȋ": "I",
"Ỉ": "I",
"Ị": "I",
"Ð": "D",
"Ñ": "N",
"Ò": "O",
"Ó": "O",
"Ô": "O",
"Õ": "O",
"Ö": "O",
"Ø": "O",
"Ố": "O",
"Ṍ": "O",
"Ṓ": "O",
"Ȏ": "O",
"Ỏ": "O",
"Ọ": "O",
"Ổ": "O",
"Ỗ": "O",
"Ộ": "O",
"Ờ": "O",
"Ở": "O",
"Ỡ": "O",
"Ớ": "O",
"Ợ": "O",
"Ù": "U",
"Ú": "U",
"Û": "U",
"Ü": "U",
"Ủ": "U",
"Ụ": "U",
"Ử": "U",
"Ữ": "U",
"Ự": "U",
"Ý": "Y",
"à": "a",
"á": "a",
"â": "a",
"ã": "a",
"ä": "a",
"å": "a",
"ấ": "a",
"ắ": "a",
"ẳ": "a",
"ẵ": "a",
"ặ": "a",
"æ": "ae",
"ầ": "a",
"ằ": "a",
"ȃ": "a",
"ả": "a",
"ạ": "a",
"ẩ": "a",
"ẫ": "a",
"ậ": "a",
"ç": "c",
"ḉ": "c",
"è": "e",
"é": "e",
"ê": "e",
"ë": "e",
"ế": "e",
"ḗ": "e",
"ề": "e",
"ḕ": "e",
"ḝ": "e",
"ȇ": "e",
"ẻ": "e",
"ẽ": "e",
"ẹ": "e",
"ể": "e",
"ễ": "e",
"ệ": "e",
"ì": "i",
"í": "i",
"î": "i",
"ï": "i",
"ḯ": "i",
"ȋ": "i",
"ỉ": "i",
"ị": "i",
"ð": "d",
"ñ": "n",
"ò": "o",
"ó": "o",
"ô": "o",
"õ": "o",
"ö": "o",
"ø": "o",
"ố": "o",
"ṍ": "o",
"ṓ": "o",
"ȏ": "o",
"ỏ": "o",
"ọ": "o",
"ổ": "o",
"ỗ": "o",
"ộ": "o",
"ờ": "o",
"ở": "o",
"ỡ": "o",
"ớ": "o",
"ợ": "o",
"ù": "u",
"ú": "u",
"û": "u",
"ü": "u",
"ủ": "u",
"ụ": "u",
"ử": "u",
"ữ": "u",
"ự": "u",
"ý": "y",
"ÿ": "y",
"Ā": "A",
"ā": "a",
"Ă": "A",
"ă": "a",
"Ą": "A",
"ą": "a",
"Ć": "C",
"ć": "c",
"Ĉ": "C",
"ĉ": "c",
"Ċ": "C",
"ċ": "c",
"Č": "C",
"č": "c",
"C̆": "C",
"c̆": "c",
"Ď": "D",
"ď": "d",
"Đ": "D",
"đ": "d",
"Ē": "E",
"ē": "e",
"Ĕ": "E",
"ĕ": "e",
"Ė": "E",
"ė": "e",
"Ę": "E",
"ę": "e",
"Ě": "E",
"ě": "e",
"Ĝ": "G",
"Ǵ": "G",
"ĝ": "g",
"ǵ": "g",
"Ğ": "G",
"ğ": "g",
"Ġ": "G",
"ġ": "g",
"Ģ": "G",
"ģ": "g",
"Ĥ": "H",
"ĥ": "h",
"Ħ": "H",
"ħ": "h",
"Ḫ": "H",
"ḫ": "h",
"Ĩ": "I",
"ĩ": "i",
"Ī": "I",
"ī": "i",
"Ĭ": "I",
"ĭ": "i",
"Į": "I",
"į": "i",
"İ": "I",
"ı": "i",
"IJ": "IJ",
"ij": "ij",
"Ĵ": "J",
"ĵ": "j",
"Ķ": "K",
"ķ": "k",
"Ḱ": "K",
"ḱ": "k",
"K̆": "K",
"k̆": "k",
"Ĺ": "L",
"ĺ": "l",
"Ļ": "L",
"ļ": "l",
"Ľ": "L",
"ľ": "l",
"Ŀ": "L",
"ŀ": "l",
"Ł": "l",
"ł": "l",
"Ḿ": "M",
"ḿ": "m",
"M̆": "M",
"m̆": "m",
"Ń": "N",
"ń": "n",
"Ņ": "N",
"ņ": "n",
"Ň": "N",
"ň": "n",
"ʼn": "n",
"N̆": "N",
"n̆": "n",
"Ō": "O",
"ō": "o",
"Ŏ": "O",
"ŏ": "o",
"Ő": "O",
"ő": "o",
"Œ": "OE",
"œ": "oe",
"P̆": "P",
"p̆": "p",
"Ŕ": "R",
"ŕ": "r",
"Ŗ": "R",
"ŗ": "r",
"Ř": "R",
"ř": "r",
"R̆": "R",
"r̆": "r",
"Ȓ": "R",
"ȓ": "r",
"Ś": "S",
"ś": "s",
"Ŝ": "S",
"ŝ": "s",
"Ş": "S",
"Ș": "S",
"ș": "s",
"ş": "s",
"Š": "S",
"š": "s",
"Ţ": "T",
"ţ": "t",
"ț": "t",
"Ț": "T",
"Ť": "T",
"ť": "t",
"Ŧ": "T",
"ŧ": "t",
"T̆": "T",
"t̆": "t",
"Ũ": "U",
"ũ": "u",
"Ū": "U",
"ū": "u",
"Ŭ": "U",
"ŭ": "u",
"Ů": "U",
"ů": "u",
"Ű": "U",
"ű": "u",
"Ų": "U",
"ų": "u",
"Ȗ": "U",
"ȗ": "u",
"V̆": "V",
"v̆": "v",
"Ŵ": "W",
"ŵ": "w",
"Ẃ": "W",
"ẃ": "w",
"X̆": "X",
"x̆": "x",
"Ŷ": "Y",
"ŷ": "y",
"Ÿ": "Y",
"Y̆": "Y",
"y̆": "y",
"Ź": "Z",
"ź": "z",
"Ż": "Z",
"ż": "z",
"Ž": "Z",
"ž": "z",
"ſ": "s",
"ƒ": "f",
"Ơ": "O",
"ơ": "o",
"Ư": "U",
"ư": "u",
"Ǎ": "A",
"ǎ": "a",
"Ǐ": "I",
"ǐ": "i",
"Ǒ": "O",
"ǒ": "o",
"Ǔ": "U",
"ǔ": "u",
"Ǖ": "U",
"ǖ": "u",
"Ǘ": "U",
"ǘ": "u",
"Ǚ": "U",
"ǚ": "u",
"Ǜ": "U",
"ǜ": "u",
"Ứ": "U",
"ứ": "u",
"Ṹ": "U",
"ṹ": "u",
"Ǻ": "A",
"ǻ": "a",
"Ǽ": "AE",
"ǽ": "ae",
"Ǿ": "O",
"ǿ": "o",
"Þ": "TH",
"þ": "th",
"Ṕ": "P",
"ṕ": "p",
"Ṥ": "S",
"ṥ": "s",
"X́": "X",
"x́": "x",
"Ѓ": "Г",
"ѓ": "г",
"Ќ": "К",
"ќ": "к",
"A̋": "A",
"a̋": "a",
"E̋": "E",
"e̋": "e",
"I̋": "I",
"i̋": "i",
"Ǹ": "N",
"ǹ": "n",
"Ồ": "O",
"ồ": "o",
"Ṑ": "O",
"ṑ": "o",
"Ừ": "U",
"ừ": "u",
"Ẁ": "W",
"ẁ": "w",
"Ỳ": "Y",
"ỳ": "y",
"Ȁ": "A",
"ȁ": "a",
"Ȅ": "E",
"ȅ": "e",
"Ȉ": "I",
"ȉ": "i",
"Ȍ": "O",
"ȍ": "o",
"Ȑ": "R",
"ȑ": "r",
"Ȕ": "U",
"ȕ": "u",
"B̌": "B",
"b̌": "b",
"Č̣": "C",
"č̣": "c",
"Ê̌": "E",
"ê̌": "e",
"F̌": "F",
"f̌": "f",
"Ǧ": "G",
"ǧ": "g",
"Ȟ": "H",
"ȟ": "h",
"J̌": "J",
"ǰ": "j",
"Ǩ": "K",
"ǩ": "k",
"M̌": "M",
"m̌": "m",
"P̌": "P",
"p̌": "p",
"Q̌": "Q",
"q̌": "q",
"Ř̩": "R",
"ř̩": "r",
"Ṧ": "S",
"ṧ": "s",
"V̌": "V",
"v̌": "v",
"W̌": "W",
"w̌": "w",
"X̌": "X",
"x̌": "x",
"Y̌": "Y",
"y̌": "y",
"A̧": "A",
"a̧": "a",
"B̧": "B",
"b̧": "b",
"Ḑ": "D",
"ḑ": "d",
"Ȩ": "E",
"ȩ": "e",
"Ɛ̧": "E",
"ɛ̧": "e",
"Ḩ": "H",
"ḩ": "h",
"I̧": "I",
"i̧": "i",
"Ɨ̧": "I",
"ɨ̧": "i",
"M̧": "M",
"m̧": "m",
"O̧": "O",
"o̧": "o",
"Q̧": "Q",
"q̧": "q",
"U̧": "U",
"u̧": "u",
"X̧": "X",
"x̧": "x",
"Z̧": "Z",
"z̧": "z",
"й":"и",
"Й":"И",
"ё":"е",
"Ё":"Е",
};
var chars = Object.keys(characterMap).join('|');
var allAccents = new RegExp(chars, 'g');
var firstAccent = new RegExp(chars, '');
function matcher(match) {
return characterMap[match];
}
var removeAccents = function(string) {
return string.replace(allAccents, matcher);
};
var hasAccents = function(string) {
return !!string.match(firstAccent);
};
module.exports = removeAccents;
module.exports.has = hasAccents;
module.exports.remove = removeAccents;
+4
View File
@@ -0,0 +1,4 @@
module.exports = {
testEnvironment: 'node',
testMatch: [ '<rootDir>/test.js' ],
};
+53
View File
@@ -0,0 +1,53 @@
{
"name": "remove-accents",
"version": "0.5.0",
"description": "Converting the accented characters to their corresponding non-accented ASCII characters.",
"main": "index.js",
"dependencies": {},
"devDependencies": {
"jest": "^29.6.2"
},
"scripts": {
"test": "jest -c=jest.config.js"
},
"repository": {
"type": "git",
"url": "https://github.com/tyxla/remove-accents"
},
"keywords": [
"accent",
"accents",
"remove",
"diacritic",
"clean",
"formatting",
"umlaut",
"grave",
"circumflex",
"tilde",
"acute"
],
"author": {
"name": "Marin Atanasov",
"email": "contact@marinatanasov.com",
"url": "http://marinatanasov.com"
},
"contributors": [
"tyxla",
"andreialecu",
"Soreine",
"CodeMan99",
"gollenia",
"glebtv",
"jsnajdr",
"Alorel",
"michaelkirk",
"huy-vuong"
],
"bugs": {
"url": "https://github.com/tyxla/remove-accents/issues"
},
"homepage": "https://github.com/tyxla/remove-accents",
"license": "MIT",
"typings": "./index.d.ts"
}
+47
View File
@@ -0,0 +1,47 @@
var removeAccents = require("./");
test("remove accents from string", function () {
var input =
"ÀÁÂÃÄÅẤẮÆẦẰẢẠẨẪẬÇḈÈÉÊËẾḖỀḔẺẼẸỂỄỆÌÍÎÏḮỈỊÐÑÒÓÔÕÖØỐṌṒỎỌỔỖỘỜỞỠỚỢÙÚÛÜỦỤỬỮỰÝàáâãäåấắæầằảạẩẫậçḉèéêëếḗềḕẻẽẹểễệìíîïḯỉịñòóôõöøốṍṓỏọổỗộờởỡớợùúûüủụửữựýÿĀāĂ㥹ĆćĈĉĊċČčĎďĐđĒēĔĕĖėĘęĚěĜĝĞğĠġĢģǴǵĤĥĦħĨĩĪīĬĭĮįİıIJijĴĵĶķḰḱĹĺĻļĽľĿŀŁłḾḿŃńŅņŇňʼnŌōŎŏŐőŒœŔŕŖŗŘřŚśŜŝŞşŠšŢţŤťŦŧŨũŪūŬŭŮůŰűŲųŴŵẂẃŶŷŸŹźŻżŽžſƒƠơƯưǍǎǏǐǑǒǓǔǕǖǗǘǙǚǛǜỨứṸṹǺǻǼǽǾǿðÞþṔṕṤṥX́x́ЃѓЌќA̋a̋E̋e̋I̋i̋ǸǹỒồṐṑỪừẀẁỲỳȀȁȄȅȈȉȌȍȐȑȔȕẲẴẶḜẳẵặḝC̆c̆ḪḫK̆k̆M̆m̆N̆n̆P̆p̆R̆r̆T̆t̆V̆v̆X̆x̆Y̆y̆ȂȆȊȎȃȇȋȏȒȓȖȗșțȘȚB̌b̌F̌f̌ǦǧȞȟJ̌ǰǨǩM̌m̌P̌p̌Q̌q̌ṦṧV̌v̌W̌w̌X̌x̌Y̌y̌A̧a̧B̧b̧ḐḑȨȩƐ̧ɛ̧ḨḩI̧i̧Ɨ̧ɨ̧M̧m̧O̧o̧Q̧q̧U̧u̧X̧x̧Z̧z";
var output = removeAccents(input);
var expected =
"AAAAAAAAAEAAAAAAACCEEEEEEEEEEEEEEIIIIIIIDNOOOOOOOOOOOOOOOOOOOUUUUUUUUUYaaaaaaaaaeaaaaaaacceeeeeeeeeeeeeeiiiiiiinooooooooooooooooooouuuuuuuuuyyAaAaAaCcCcCcCcDdDdEeEeEeEeEeGgGgGgGgGgHhHhIiIiIiIiIiIJijJjKkKkLlLlLlLlllMmNnNnNnnOoOoOoOEoeRrRrRrSsSsSsSsTtTtTtUuUuUuUuUuUuWwWwYyYZzZzZzsfOoUuAaIiOoUuUuUuUuUuUuUuAaAEaeOodTHthPpSsXxГгКкAaEeIiNnOoOoUuWwYyAaEeIiOoRrUuAAAEaaaeCcHhKkMmNnPpRrTtVvXxYyAEIOaeioRrUustSTBbFfGgHhJjKkMmPpQqSsVvWwXxYyAaBbDdEeEeHhIiIiMmOoQqUuXxZz";
expect(output).toBe(expected);
});
test("remove cyrillic accents from string", function () {
var input = "ЁёЙй";
var output = removeAccents(input);
var expected = "ЕеИи";
expect(output).toBe(expected);
});
test("do not modify non-accented strings", function () {
var input =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz123456789.,:;~`!@#$%^&*()-_=+[]{}'\"|\\<>?/eEиИ";
var output = removeAccents(input);
expect(output).toBe(input);
});
test(".has can detect accents", function () {
expect(removeAccents.has("À")).toBe(true);
expect(removeAccents.has("Löwe")).toBe(true);
expect(removeAccents.has("A")).toBe(false);
expect(removeAccents.has("Panther")).toBe(false);
});
test(".remove method", function () {
expect(removeAccents.toString()).toBe(removeAccents.remove.toString());
expect(removeAccents.remove("cat")).toBe("cat");
expect(removeAccents.remove("Pokémon")).toBe("Pokemon");
});
// See https://github.com/tyxla/remove-accents/issues/12
test("ß is not accented", function () {
expect(removeAccents.remove("Straße")).toBe("Straße");
});