Extract tags

.gitignore

@@ -1,3 +1,4 @@
+node_modules
 elm-stuff
 target
 js/*

Makefile

@@ -30,11 +30,11 @@ target/debug/elmojinput: js/main.js src/**
 target/release/elmojinput: js/main.min.js src/**
 	cargo build --release
 
-js/emoji.txt:
+js/emoji.html:
-	@curl https://unicode.org/Public/emoji/14.0/emoji-test.txt -o $(BUILD_DIR)/emoji.txt
+	@curl https://unicode.org/emoji/charts/emoji-list.html -o $(BUILD_DIR)/emoji.html
 
-elm/Emoji.elm: js/emoji.txt extract.js
+elm/Emoji.elm: js/emoji.html extract.js
 	@node extract.js > elm/Emoji.elm
 
 clean:
-	@rm -rf $(BUILD_DIR)/{main.js,main.min.js,emoji.txt} elm/Emoji.elm
+	@rm -rf $(BUILD_DIR)/{main.js,main.min.js,emoji.html} elm/Emoji.elm

elm/Main.elm

@@ -130,8 +130,6 @@ header model =
                               else
                                 Border.width 1
                             , Border.rounded 5
-                            , Element.width Element.fill
-                            , Element.height Element.fill
                             ]
                             { label = Element.el [ Element.centerX, Element.centerY ] (Element.text (Emoji.categoryEmoji x).unicode)
                             , onPress = Just (CategoryClicked x)
@@ -205,8 +203,8 @@ port copy : String -> Cmd msg
 -- UTILS --
 
 
-minimum : ( comparable, List comparable ) -> comparable
+minimum : comparable -> List comparable -> comparable
-minimum ( h, t ) =
+minimum h t =
     case List.minimum t of
         Nothing ->
             h
@@ -215,8 +213,8 @@ minimum ( h, t ) =
             min h v
 
 
-maximum : ( comparable, List comparable ) -> comparable
+maximum : comparable -> List comparable -> comparable
-maximum ( h, t ) =
+maximum h t =
     case List.maximum t of
         Nothing ->
             h

extract.js

@@ -1,35 +1,50 @@
 const fs = require('fs');
+const decode = require('decode-html');
+const { parse } = require('node-html-parser');
 
 function formatEmoji(emoji) {
-    return ('{ name = "' + emoji.name + '", unicode = "' + emoji.unicode + '" }');
+    return (
+        '{ name = "' + emoji.name +
+        '", unicode = "' + emoji.unicode +
+        '", tags = [ ' + emoji.tags.map(x => '"' + x + '"').join(', ') +
+        ' ] }'
+    );
 }
 
-let text = fs.readFileSync('js/emoji.txt',  'utf-8');
+let html = parse(fs.readFileSync('js/emoji.html',  'utf-8'));
+let table = html.getElementsByTagName('table')[0];
+
 let emojis = {};
 let currentEmojis = null;
 
-for (let line of text.split('\n')) {
+for (let element of table.childNodes) {
-    if (line.startsWith('#')) {
+    // Skip text
-        if (line.startsWith('# group:')) {
+    if (element.nodeType === 3) continue;
-            let name = line.split(':')[1].split(' ')[1].toLowerCase();
+
-            emojis[name] = [];
+    if (element.rawTagName === 'tr') {
-            currentEmojis = emojis[name];
+        let cols = element.childNodes.filter(x => x.nodeType !== 3);
+        let firstCol = cols[0];
+
+        if (firstCol.classList.contains('bighead')) {
+            let name = decode(firstCol.childNodes.filter(x => x.nodeType !== 3)[0].childNodes[0]._rawText)
+                .split(' ')[0]
+                .toLowerCase();
+
+            currentEmojis = [];
+            emojis[name] = currentEmojis;
         }
-        continue;
-    }
 
-    if (line.length === 0) {
+        if (firstCol.rawTagName === 'td') {
-        continue;
+            // We're in an emoji line
-    }
+            let name = decode(cols[3].childNodes[0]._rawText);
+            let tags = decode(cols[4].childNodes[0]._rawText).split('|').map(x => x.trim());
+            let unicode = cols[2].childNodes[0].childNodes[0].rawAttrs.split("'")[1];
+            currentEmojis.push({
+                unicode, name, tags
+            });
+        }
 
-    let end = line.split('#')[1];
+    }
-    let split = end.split(' ');
-    let emoji = split[1];
-    let name = split.slice(3).join(' ');
-    currentEmojis.push({
-        name,
-        unicode: emoji,
-    });
 }
 
 delete(emojis.component);
@@ -42,6 +57,7 @@ console.log('\n');
 console.log('type alias Emoji =');
 console.log('    { name : String');
 console.log('    , unicode : String');
+console.log('    , tags : List String');
 console.log('    }');
 console.log('\n');
 

package-lock.json

@@ -0,0 +1,225 @@
+{
+  "name": "emojinput",
+  "lockfileVersion": 2,
+  "requires": true,
+  "packages": {
+    "": {
+      "dependencies": {
+        "decode-html": "^2.0.0",
+        "node-html-parser": "^5.2.0"
+      }
+    },
+    "node_modules/boolbase": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-1.0.0.tgz",
+      "integrity": "sha1-aN/1++YMUes3cl6p4+0xDcwed24="
+    },
+    "node_modules/css-select": {
+      "version": "4.2.1",
+      "resolved": "https://registry.npmjs.org/css-select/-/css-select-4.2.1.tgz",
+      "integrity": "sha512-/aUslKhzkTNCQUB2qTX84lVmfia9NyjP3WpDGtj/WxhwBzWBYUV3DgUpurHTme8UTPcPlAD1DJ+b0nN/t50zDQ==",
+      "dependencies": {
+        "boolbase": "^1.0.0",
+        "css-what": "^5.1.0",
+        "domhandler": "^4.3.0",
+        "domutils": "^2.8.0",
+        "nth-check": "^2.0.1"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/css-what": {
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/css-what/-/css-what-5.1.0.tgz",
+      "integrity": "sha512-arSMRWIIFY0hV8pIxZMEfmMI47Wj3R/aWpZDDxWYCPEiOMv6tfOrnpDtgxBYPEQD4V0Y/958+1TdC3iWTFcUPw==",
+      "engines": {
+        "node": ">= 6"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/decode-html": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/decode-html/-/decode-html-2.0.0.tgz",
+      "integrity": "sha1-fQqIfORCgOYJeKcH67f4CB/WHqo="
+    },
+    "node_modules/dom-serializer": {
+      "version": "1.3.2",
+      "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-1.3.2.tgz",
+      "integrity": "sha512-5c54Bk5Dw4qAxNOI1pFEizPSjVsx5+bpJKmL2kPn8JhBUq2q09tTCa3mjijun2NfK78NMouDYNMBkOrPZiS+ig==",
+      "dependencies": {
+        "domelementtype": "^2.0.1",
+        "domhandler": "^4.2.0",
+        "entities": "^2.0.0"
+      },
+      "funding": {
+        "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1"
+      }
+    },
+    "node_modules/domelementtype": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-2.2.0.tgz",
+      "integrity": "sha512-DtBMo82pv1dFtUmHyr48beiuq792Sxohr+8Hm9zoxklYPfa6n0Z3Byjj2IV7bmr2IyqClnqEQhfgHJJ5QF0R5A==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ]
+    },
+    "node_modules/domhandler": {
+      "version": "4.3.0",
+      "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-4.3.0.tgz",
+      "integrity": "sha512-fC0aXNQXqKSFTr2wDNZDhsEYjCiYsDWl3D01kwt25hm1YIPyDGHvvi3rw+PLqHAl/m71MaiF7d5zvBr0p5UB2g==",
+      "dependencies": {
+        "domelementtype": "^2.2.0"
+      },
+      "engines": {
+        "node": ">= 4"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/domhandler?sponsor=1"
+      }
+    },
+    "node_modules/domutils": {
+      "version": "2.8.0",
+      "resolved": "https://registry.npmjs.org/domutils/-/domutils-2.8.0.tgz",
+      "integrity": "sha512-w96Cjofp72M5IIhpjgobBimYEfoPjx1Vx0BSX9P30WBdZW2WIKU0T1Bd0kz2eNZ9ikjKgHbEyKx8BB6H1L3h3A==",
+      "dependencies": {
+        "dom-serializer": "^1.0.1",
+        "domelementtype": "^2.2.0",
+        "domhandler": "^4.2.0"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/domutils?sponsor=1"
+      }
+    },
+    "node_modules/entities": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-2.2.0.tgz",
+      "integrity": "sha512-p92if5Nz619I0w+akJrLZH0MX0Pb5DX39XOwQTtXSdQQOaYH03S1uIQp4mhOZtAXrxq4ViO67YTiLBo2638o9A==",
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
+    "node_modules/he": {
+      "version": "1.2.0",
+      "resolved": "https://registry.npmjs.org/he/-/he-1.2.0.tgz",
+      "integrity": "sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw==",
+      "bin": {
+        "he": "bin/he"
+      }
+    },
+    "node_modules/node-html-parser": {
+      "version": "5.2.0",
+      "resolved": "https://registry.npmjs.org/node-html-parser/-/node-html-parser-5.2.0.tgz",
+      "integrity": "sha512-fmiwLfQu+J2A0zjwSEkztSHexAf5qq/WoiL/Hgo1K7JpfEP+OGWY5maG0kGaM+IFVdixF/1QbyXaQ3h4cGfeLw==",
+      "dependencies": {
+        "css-select": "^4.1.3",
+        "he": "1.2.0"
+      }
+    },
+    "node_modules/nth-check": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-2.0.1.tgz",
+      "integrity": "sha512-it1vE95zF6dTT9lBsYbxvqh0Soy4SPowchj0UBGj/V6cTPnXXtQOPUbhZ6CmGzAD/rW22LQK6E96pcdJXk4A4w==",
+      "dependencies": {
+        "boolbase": "^1.0.0"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/nth-check?sponsor=1"
+      }
+    }
+  },
+  "dependencies": {
+    "boolbase": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-1.0.0.tgz",
+      "integrity": "sha1-aN/1++YMUes3cl6p4+0xDcwed24="
+    },
+    "css-select": {
+      "version": "4.2.1",
+      "resolved": "https://registry.npmjs.org/css-select/-/css-select-4.2.1.tgz",
+      "integrity": "sha512-/aUslKhzkTNCQUB2qTX84lVmfia9NyjP3WpDGtj/WxhwBzWBYUV3DgUpurHTme8UTPcPlAD1DJ+b0nN/t50zDQ==",
+      "requires": {
+        "boolbase": "^1.0.0",
+        "css-what": "^5.1.0",
+        "domhandler": "^4.3.0",
+        "domutils": "^2.8.0",
+        "nth-check": "^2.0.1"
+      }
+    },
+    "css-what": {
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/css-what/-/css-what-5.1.0.tgz",
+      "integrity": "sha512-arSMRWIIFY0hV8pIxZMEfmMI47Wj3R/aWpZDDxWYCPEiOMv6tfOrnpDtgxBYPEQD4V0Y/958+1TdC3iWTFcUPw=="
+    },
+    "decode-html": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/decode-html/-/decode-html-2.0.0.tgz",
+      "integrity": "sha1-fQqIfORCgOYJeKcH67f4CB/WHqo="
+    },
+    "dom-serializer": {
+      "version": "1.3.2",
+      "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-1.3.2.tgz",
+      "integrity": "sha512-5c54Bk5Dw4qAxNOI1pFEizPSjVsx5+bpJKmL2kPn8JhBUq2q09tTCa3mjijun2NfK78NMouDYNMBkOrPZiS+ig==",
+      "requires": {
+        "domelementtype": "^2.0.1",
+        "domhandler": "^4.2.0",
+        "entities": "^2.0.0"
+      }
+    },
+    "domelementtype": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-2.2.0.tgz",
+      "integrity": "sha512-DtBMo82pv1dFtUmHyr48beiuq792Sxohr+8Hm9zoxklYPfa6n0Z3Byjj2IV7bmr2IyqClnqEQhfgHJJ5QF0R5A=="
+    },
+    "domhandler": {
+      "version": "4.3.0",
+      "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-4.3.0.tgz",
+      "integrity": "sha512-fC0aXNQXqKSFTr2wDNZDhsEYjCiYsDWl3D01kwt25hm1YIPyDGHvvi3rw+PLqHAl/m71MaiF7d5zvBr0p5UB2g==",
+      "requires": {
+        "domelementtype": "^2.2.0"
+      }
+    },
+    "domutils": {
+      "version": "2.8.0",
+      "resolved": "https://registry.npmjs.org/domutils/-/domutils-2.8.0.tgz",
+      "integrity": "sha512-w96Cjofp72M5IIhpjgobBimYEfoPjx1Vx0BSX9P30WBdZW2WIKU0T1Bd0kz2eNZ9ikjKgHbEyKx8BB6H1L3h3A==",
+      "requires": {
+        "dom-serializer": "^1.0.1",
+        "domelementtype": "^2.2.0",
+        "domhandler": "^4.2.0"
+      }
+    },
+    "entities": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-2.2.0.tgz",
+      "integrity": "sha512-p92if5Nz619I0w+akJrLZH0MX0Pb5DX39XOwQTtXSdQQOaYH03S1uIQp4mhOZtAXrxq4ViO67YTiLBo2638o9A=="
+    },
+    "he": {
+      "version": "1.2.0",
+      "resolved": "https://registry.npmjs.org/he/-/he-1.2.0.tgz",
+      "integrity": "sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw=="
+    },
+    "node-html-parser": {
+      "version": "5.2.0",
+      "resolved": "https://registry.npmjs.org/node-html-parser/-/node-html-parser-5.2.0.tgz",
+      "integrity": "sha512-fmiwLfQu+J2A0zjwSEkztSHexAf5qq/WoiL/Hgo1K7JpfEP+OGWY5maG0kGaM+IFVdixF/1QbyXaQ3h4cGfeLw==",
+      "requires": {
+        "css-select": "^4.1.3",
+        "he": "1.2.0"
+      }
+    },
+    "nth-check": {
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-2.0.1.tgz",
+      "integrity": "sha512-it1vE95zF6dTT9lBsYbxvqh0Soy4SPowchj0UBGj/V6cTPnXXtQOPUbhZ6CmGzAD/rW22LQK6E96pcdJXk4A4w==",
+      "requires": {
+        "boolbase": "^1.0.0"
+      }
+    }
+  }
+}

package.json

@@ -0,0 +1,6 @@
+{
+  "dependencies": {
+    "decode-html": "^2.0.0",
+    "node-html-parser": "^5.2.0"
+  }
+}