Add synchronous API/tests/docs, general cleanup

This makes the API simpler/lighter to use in non-node/browserify
environments, or when dealing with synchronous-only APIs.

.gitignore

@@ -0,0 +1,3 @@
+node_modules
+npm-debug.log
+.DS_Store

.npmignore

@@ -1 +1,4 @@
-node_modules/
+node_modules
+npm-debug.log
+.DS_Store
+test/

LICENSE.md

@@ -0,0 +1,10 @@
+The MIT License (MIT)
+=====================
+
+Copyright (c) 2014 [Chris Dickinson](http://github.com/chrisdickinson)
+
+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.

README.md

@@ -1,36 +1,42 @@
 # glsl-tokenizer
 
-a [readable / writable stream](https://github.com/dominictarr/stream-spec#through-sync-writable-and-readable-aka-filter) that maps input to glsl tokens, if possible.
-
-```javascript
-
-  var fs = require('fs')
-    , tokens = require('glsl-tokenizer')()
-
-  fs.createReadStream('some.glsl')
-    .pipe(tokens)
-    .on('data', function(token) {
-      console.log(token.data, token.position, token.type)
-    })
-
+Maps GLSL string data into GLSL tokens, either synchronously or using a
+streaming API.
+
+``` javascript
+var tokenString = require('glsl-tokenizer/string')
+var tokenStream = require('glsl-tokenizer/stream')
+var fs = require('fs')
+
+// Synchronously:
+var tokens = tokenString(fs.readFileSync('some.glsl'))
+
+// Streaming API:
+fs.createReadStream('some.glsl')
+  .pipe(tokenStream())
+  .on('data', function(token) {
+    console.log(token.data, token.position, token.type)
+  })
 ```
 
 # API
 
-### tokens = require('glsl-tokenizer')()
+## tokens = require('glsl-tokenizer/string')(src)
 
-return a tokenizer stream instance.
+Returns an array of `tokens` given the GLSL source string `src`
 
-emits 'data' events whenever a token is parsed with a token object as output.
+## stream = require('glsl-tokenizer/stream')()
 
-# tokens
+Emits 'data' events whenever a token is parsed with a token object as output.
 
-```javascript
+# Tokens
 
+```javascript
 { 'type': TOKEN_TYPE
 , 'data': "string of constituent data"
-, 'position': integer position within the data stream }
-
+, 'position': integer position within the GLSL source
+, 'line': line number within the GLSL source
+, 'column': column number within the GLSL source }
 ```
 
 The available token types are:
@@ -39,14 +45,14 @@ The available token types are:
 * `line-comment`: `// ... \n`
 * `preprocessor`: `# ... \n`
 * `operator`: Any operator. If it looks like punctuation, it's an operator.
-* `integer`
 * `float`: Optionally suffixed with `f`
 * `ident`: User defined identifier.
-* `builtin`: Builtin function
-* `keyword`
+* `builtin`: Builtin function.
+* `eof`: Emitted on `end`; data will === `'(eof)'`.
+* `integer`
 * `whitespace`
-* `eof`: emitted on `end`; data will === `'(eof)'`.
+* `keyword`
 
 # License
 
-MIT
+MIT, see [LICENSE.md](LICENSE.md) for further information.

index.js

@@ -1,14 +1,12 @@
 module.exports = tokenize
 
-var through = require('through')
-
 var literals = require('./lib/literals')
   , operators = require('./lib/operators')
   , builtins = require('./lib/builtins')
 
 var NORMAL = 999          // <-- never emitted
-  , TOKEN = 9999          // <-- never emitted 
-  , BLOCK_COMMENT = 0 
+  , TOKEN = 9999          // <-- never emitted
+  , BLOCK_COMMENT = 0
   , LINE_COMMENT = 1
   , PREPROCESSOR = 2
   , OPERATOR = 3
@@ -18,7 +16,7 @@ var NORMAL = 999          // <-- never emitted
   , BUILTIN = 7
   , KEYWORD = 8
   , WHITESPACE = 9
-  , EOF = 10 
+  , EOF = 10
   , HEX = 11
 
 var map = [
@@ -37,14 +35,13 @@ var map = [
 ]
 
 function tokenize() {
-  var stream = through(write, end)
-
   var i = 0
     , total = 0
-    , mode = NORMAL 
+    , mode = NORMAL
     , c
     , last
     , content = []
+    , tokens = []
     , token_idx = 0
     , token_offs = 0
     , line = 1
@@ -55,11 +52,15 @@ function tokenize() {
     , input = ''
     , len
 
-  return stream
+  return function(data) {
+    tokens = []
+    if (data !== null) return write(data)
+    return end()
+  }
 
   function token(data) {
-    if(data.length) {
-      stream.queue({
+    if (data.length) {
+      tokens.push({
         type: map[mode]
       , data: data
       , position: start
@@ -71,7 +72,7 @@ function tokenize() {
 
   function write(chunk) {
     i = 0
-    input += chunk.toString()
+    input += chunk
     len = input.length
 
     var last
@@ -102,7 +103,8 @@ function tokenize() {
 
     total += i
     input = input.slice(i)
-  } 
+    return tokens
+  }
 
   function end(chunk) {
     if(content.length) {
@@ -111,8 +113,7 @@ function tokenize() {
 
     mode = EOF
     token('(eof)')
-
-    stream.queue(null)
+    return tokens
   }
 
   function normal() {
@@ -209,7 +210,7 @@ function tokenize() {
 
     if(c === '.' && content.length) {
       while(determine_operator(content));
-      
+
       mode = FLOAT
       return i
     }
@@ -239,11 +240,11 @@ function tokenize() {
 
     do {
       idx = operators.indexOf(buf.slice(0, buf.length + j).join(''))
-      if(idx === -1) { 
+      if(idx === -1) {
         j -= 1
         continue
       }
-      
+
       token(operators[idx])
 
       start += operators[idx].length
@@ -261,7 +262,7 @@ function tokenize() {
 
     content.push(c)
     last = c
-    return i + 1    
+    return i + 1
   }
 
   function integer() {

package.json

@@ -2,7 +2,7 @@
   "name": "glsl-tokenizer",
   "version": "1.1.1",
   "description": "r/w stream of glsl tokens",
-  "main": "index.js",
+  "main": "stream.js",
   "directories": {
     "test": "test"
   },
@@ -12,7 +12,7 @@
     "Chris Dickinson <chris@neversaw.us> (http://neversaw.us)"
   ],
   "scripts": {
-    "test": "node test/index.js"
+    "test": "node test/index.js | tap-spec"
   },
   "repository": {
     "type": "git",
@@ -26,6 +26,10 @@
   "author": "Chris Dickinson <chris@neversaw.us>",
   "license": "MIT",
   "dependencies": {
-    "through": "X.X.X"
+    "through2": "^0.6.3"
+  },
+  "devDependencies": {
+    "tap-spec": "^1.0.1",
+    "tape": "^3.0.2"
   }
 }

stream.js

@@ -0,0 +1,27 @@
+var through  = require('through2').obj
+var tokenize = require('./index')
+
+module.exports = createStream
+
+function createStream() {
+  var generator = tokenize()
+
+  return through(write, end)
+
+  function write(chunk, _, next) {
+    flush(this, chunk)
+    next()
+  }
+
+  function end() {
+    flush(this, null)
+    this.push(null)
+  }
+
+  function flush(stream, chunk) {
+    var tokens = generator(chunk)
+    for (var i = 0; i < tokens.length; i++) {
+      stream.push(tokens[i])
+    }
+  }
+}

string.js

@@ -0,0 +1,13 @@
+var tokenize = require('./index')
+
+module.exports = tokenizeString
+
+function tokenizeString(str) {
+  var generator = tokenize()
+  var tokens = []
+
+  tokens = tokens.concat(generator(str))
+  tokens = tokens.concat(generator(null))
+
+  return tokens
+}