Add offset property to position

graberzz · ai · commit f09e2961b57b · 2020-09-08T22:18:32.000-04:00
diff --git a/lib/node.d.ts b/lib/node.d.ts
@@ -21,6 +21,11 @@ export type ChildProps =
   | CommentProps
 
 export interface Position {
+  /**
+   * Source offset in file.
+   */
+  offset: number
+
   /**
    * Source line in file.
    */
diff --git a/lib/parser.js b/lib/parser.js
@@ -1,5 +1,7 @@
 'use strict'
 
+let lineColumn = require('line-column')
+
 let Declaration = require('./declaration')
 let tokenizer = require('./tokenize')
 let Comment = require('./comment')
@@ -10,6 +12,7 @@ let Rule = require('./rule')
 class Parser {
   constructor (input) {
     this.input = input
+    this.finder = lineColumn(this.input.css)
 
     this.root = new Root()
     this.current = this.root
@@ -18,7 +21,7 @@ class Parser {
     this.customProperty = false
 
     this.createTokenizer()
-    this.root.source = { input, start: { line: 1, column: 1 } }
+    this.root.source = { input, start: { offset: 0, line: 1, column: 1 } }
   }
 
   createTokenizer () {
@@ -65,8 +68,13 @@ class Parser {
 
   comment (token) {
     let node = new Comment()
-    this.init(node, token[2], token[3])
-    node.source.end = { line: token[4], column: token[5] }
+    this.init(node, token[2])
+    let pos = this.finder.fromIndex(token[3])
+    node.source.end = {
+      offset: token[3],
+      line: pos.line,
+      column: pos.col
+    }
 
     let text = token[1].slice(2, -2)
     if (/^\s*$/.test(text)) {
@@ -83,7 +91,7 @@ class Parser {
 
   emptyRule (token) {
     let node = new Rule()
-    this.init(node, token[2], token[3])
+    this.init(node, token[2])
     node.selector = ''
     node.raws.between = ''
     this.current = node
@@ -154,7 +162,7 @@ class Parser {
     tokens.pop()
 
     let node = new Rule()
-    this.init(node, tokens[0][2], tokens[0][3])
+    this.init(node, tokens[0][2])
 
     node.raws.between = this.spacesAndCommentsFromEnd(tokens)
     this.raw(node, 'selector', tokens)
@@ -170,17 +178,32 @@ class Parser {
       this.semicolon = true
       tokens.pop()
     }
-    if (last[4]) {
-      node.source.end = { line: last[4], column: last[5] }
+    if (last[3]) {
+      let pos = this.finder.fromIndex(last[3])
+      node.source.end = {
+        offset: last[3],
+        line: pos.line,
+        column: pos.col
+      }
     } else {
-      node.source.end = { line: last[2], column: last[3] }
+      let pos = this.finder.fromIndex(last[2])
+      node.source.end = {
+        offset: last[2],
+        line: pos.line,
+        column: pos.col
+      }
     }
 
     while (tokens[0][0] !== 'word') {
       if (tokens.length === 1) this.unknownWord(tokens)
       node.raws.before += tokens.shift()[1]
     }
-    node.source.start = { line: tokens[0][2], column: tokens[0][3] }
+    let pos = this.finder.fromIndex(tokens[0][2])
+    node.source.start = {
+      offset: tokens[0][2],
+      line: pos.line,
+      column: pos.col
+    }
 
     node.prop = ''
     while (tokens.length) {
@@ -264,7 +287,7 @@ class Parser {
     if (node.name === '') {
       this.unnamedAtrule(node, token)
     }
-    this.init(node, token[2], token[3])
+    this.init(node, token[2])
 
     let type
     let prev
@@ -288,7 +311,12 @@ class Parser {
 
       if (brackets.length === 0) {
         if (type === ';') {
-          node.source.end = { line: token[2], column: token[3] }
+          let pos = this.finder.fromIndex(token[2])
+          node.source.end = {
+            offset: token[2],
+            line: pos.line,
+            column: pos.col
+          }
           this.semicolon = true
           break
         } else if (type === '{') {
@@ -302,7 +330,12 @@ class Parser {
               prev = params[--shift]
             }
             if (prev) {
-              node.source.end = { line: prev[4], column: prev[5] }
+              let pos = this.finder.fromIndex(prev[4])
+              node.source.end = {
+                offset: prev[4],
+                line: pos.line,
+                column: pos.col
+              }
             }
           }
           this.end(token)
@@ -326,7 +359,12 @@ class Parser {
       this.raw(node, 'params', params)
       if (last) {
         token = params[params.length - 1]
-        node.source.end = { line: token[4], column: token[5] }
+        let pos = this.finder.fromIndex(token[3])
+        node.source.end = {
+          offset: token[3],
+          line: pos.line,
+          column: pos.col
+        }
         this.spaces = node.raws.between
         node.raws.between = ''
       }
@@ -351,7 +389,12 @@ class Parser {
     this.spaces = ''
 
     if (this.current.parent) {
-      this.current.source.end = { line: token[2], column: token[3] }
+      let pos = this.finder.fromIndex(token[2])
+      this.current.source.end = {
+        offset: token[2],
+        line: pos.line,
+        column: pos.col
+      }
       this.current = this.current.parent
     } else {
       this.unexpectedClose(token)
@@ -379,10 +422,18 @@ class Parser {
 
   // Helpers
 
-  init (node, line, column) {
+  init (node, offset) {
     this.current.push(node)
 
-    node.source = { start: { line, column }, input: this.input }
+    let pos = this.finder.fromIndex(offset) || { line: null, column: null }
+    node.source = {
+      start: {
+        offset,
+        line: pos.line,
+        column: pos.col
+      },
+      input: this.input
+    }
     node.raws.before = this.spaces
     this.spaces = ''
     if (node.type !== 'comment') this.semicolon = false
@@ -504,15 +555,18 @@ class Parser {
   // Errors
 
   unclosedBracket (bracket) {
-    throw this.input.error('Unclosed bracket', bracket[2], bracket[3])
+    let pos = this.finder.fromIndex(bracket[2])
+    throw this.input.error('Unclosed bracket', pos.line, pos.col)
   }
 
   unknownWord (tokens) {
-    throw this.input.error('Unknown word', tokens[0][2], tokens[0][3])
+    let pos = this.finder.fromIndex(tokens[0][2])
+    throw this.input.error('Unknown word', pos.line, pos.col)
   }
 
   unexpectedClose (token) {
-    throw this.input.error('Unexpected }', token[2], token[3])
+    let pos = this.finder.fromIndex(token[2])
+    throw this.input.error('Unexpected }', pos.line, pos.col)
   }
 
   unclosedBlock () {
@@ -521,11 +575,13 @@ class Parser {
   }
 
   doubleColon (token) {
-    throw this.input.error('Double colon', token[2], token[3])
+    let pos = this.finder.fromIndex(token[2])
+    throw this.input.error('Double colon', pos.line, pos.col)
   }
 
   unnamedAtrule (node, token) {
-    throw this.input.error('At-rule without name', token[2], token[3])
+    let pos = this.finder.fromIndex(token[2])
+    throw this.input.error('At-rule without name', pos.line, pos.col)
   }
 
   precheckMissedSemicolon (/* tokens */) {
@@ -545,7 +601,8 @@ class Parser {
         if (founded === 2) break
       }
     }
-    throw this.input.error('Missed semicolon', token[2], token[3])
+    let pos = this.finder.fromIndex(token[2])
+    throw this.input.error('Missed semicolon', pos.line, pos.col)
   }
 }
 
diff --git a/lib/tokenize.js b/lib/tokenize.js
@@ -102,7 +102,7 @@ module.exports = function tokenizer (input, options = {}) {
       case SEMICOLON:
       case CLOSE_PARENTHESES: {
         let controlChar = String.fromCharCode(code)
-        currentToken = [controlChar, controlChar, line, pos - offset]
+        currentToken = [controlChar, controlChar, pos]
         break
       }
 
@@ -138,31 +138,17 @@ module.exports = function tokenizer (input, options = {}) {
             }
           } while (escaped)
 
-          currentToken = [
-            'brackets',
-            css.slice(pos, next + 1),
-            line,
-            pos - offset,
-            line,
-            next - offset
-          ]
+          currentToken = ['brackets', css.slice(pos, next + 1), pos, next]
 
           pos = next
         } else {
           next = css.indexOf(')', pos + 1)
           content = css.slice(pos, next + 1)
 
           if (next === -1 || RE_BAD_BRACKET.test(content)) {
-            currentToken = ['(', '(', line, pos - offset]
+            currentToken = ['(', '(', pos]
           } else {
-            currentToken = [
-              'brackets',
-              content,
-              line,
-              pos - offset,
-              line,
-              next - offset
-            ]
+            currentToken = ['brackets', content, pos, next]
             pos = next
           }
         }
@@ -204,14 +190,7 @@ module.exports = function tokenizer (input, options = {}) {
           nextOffset = offset
         }
 
-        currentToken = [
-          'string',
-          css.slice(pos, next + 1),
-          line,
-          pos - offset,
-          nextLine,
-          next - nextOffset
-        ]
+        currentToken = ['string', css.slice(pos, next + 1), pos, next]
 
         offset = nextOffset
         line = nextLine
@@ -228,14 +207,7 @@ module.exports = function tokenizer (input, options = {}) {
           next = RE_AT_END.lastIndex - 2
         }
 
-        currentToken = [
-          'at-word',
-          css.slice(pos, next + 1),
-          line,
-          pos - offset,
-          line,
-          next - offset
-        ]
+        currentToken = ['at-word', css.slice(pos, next + 1), pos, next]
 
         pos = next
         break
@@ -269,14 +241,7 @@ module.exports = function tokenizer (input, options = {}) {
           }
         }
 
-        currentToken = [
-          'word',
-          css.slice(pos, next + 1),
-          line,
-          pos - offset,
-          line,
-          next - offset
-        ]
+        currentToken = ['word', css.slice(pos, next + 1), pos, next]
 
         pos = next
         break
@@ -305,14 +270,7 @@ module.exports = function tokenizer (input, options = {}) {
             nextOffset = offset
           }
 
-          currentToken = [
-            'comment',
-            content,
-            line,
-            pos - offset,
-            nextLine,
-            next - nextOffset
-          ]
+          currentToken = ['comment', content, pos, next]
 
           offset = nextOffset
           line = nextLine
@@ -326,14 +284,7 @@ module.exports = function tokenizer (input, options = {}) {
             next = RE_WORD_END.lastIndex - 2
           }
 
-          currentToken = [
-            'word',
-            css.slice(pos, next + 1),
-            line,
-            pos - offset,
-            line,
-            next - offset
-          ]
+          currentToken = ['word', css.slice(pos, next + 1), pos, next]
 
           buffer.push(currentToken)
 
diff --git a/package.json b/package.json
@@ -38,6 +38,7 @@
   "repository": "postcss/postcss",
   "dependencies": {
     "colorette": "^1.2.1",
+    "line-column": "^1.0.2",
     "nanoid": "^3.1.12",
     "source-map": "^0.6.1"
   },
diff --git a/test/tokenize.test.js b/test/tokenize.test.js
