js-parse - npm Package Compare versions

Comparing version 0.1.1 to 0.1.2

examples/php/lexical/keywords.json

 {
 	"symbols":{
+		"this":{
+			"terminal":true,
+			"match":"(this)",
+			"matchCaseInsensitive":true
+		},
 		"enddeclare":{
@@ -4,0 +9,0 @@ "terminal":true,

examples/php/lexical/literals.js

@@ -47,3 +47,3 @@ /**
       "terminal":true,
-      "match":"[0-9]+(\\.)?[0-9]*[e][\\-\\+]?[0-9]+",
+      "match":"[0-9]+(\\.)?[0-9]*[Ee][\\-\\+]?[0-9]+",
       "matchCaseInsensitive":true
@@ -50,0 +50,0 @@ },

examples/php/lexical/tokens.js

@@ -34,13 +34,10 @@ /**
 
-    // TODO: Potential bug here (S/R conflict)
-    "namespace-name-as-a-prefix":[
-    	["namespace-name", "literals.\\"],
-    	["literals.\\", "namespace-name", "literals.\\"],
-    	["literals.\\"],
-    	["kw.namespace", "literals.\\", "namespace-name", "literals.\\"],
-    	["kw.namespace", "literals.\\"]
-    ],
+    // Combined namespace-name-as-a-prefix with qualified name.
     "qualified-name":[
-    	["namespace-name-as-a-prefix", "literals.name"],
-    	["literals.name"]
+      ["literals.name"],
+      ["literals.\\", "literals.name"],
+      ["literals.\\", "namespace-name", "literals.\\", "literals.name"],
+      ["kw.namespace", "literals.\\", "literals.name"],
+      ["kw.namespace", "literals.\\", "namespace-name", "literals.\\", "literals.name"],
+      ["namespace-name", "literals.\\", "literals.name"]
     ]
@@ -47,0 +44,0 @@ },

examples/php/spec/primary_expressions_spec.js

@@ -9,3 +9,20 @@ var Parser = require("../../../lib").Parser.LRParser;
 	var positive_literal_cases = {
-		"$test":"tokens.variable-name"
+		"$test":"tokens.variable-name",
+		"$test12345":"tokens.variable-name",
+		"$_test12345":"tokens.variable-name",
+		"$___test12345":"tokens.variable-name",
+		"___test12345":"tokens.qualified-name",
+		"\\___test12345":"tokens.qualified-name",
+		"\\a_namespace\\___test12345":"tokens.qualified-name",
+		"\\___test12345":"tokens.qualified-name",
+		"namespace\\___test12345":"tokens.qualified-name",
+		"123456":"literals.literal",
+		"TRUE":"literals.literal",
+		"false":"literals.literal",
+		"NULL":"literals.literal",
+		"1.35E10":"literals.literal",
+		"$this":"$this",
+		"($this)":"expression-in-parens",
+		"(1.35E123)":"expression-in-parens",
+		"($test)":"expression-in-parens",
 	};
@@ -26,9 +43,12 @@
 			return function(end){
-				terminals_pd.startSymbols = [expected];
 				var parser = Parser.CreateWithLexer(terminals_pd, {"path":"./syntax"});
 				parser.on("error", function(error){ throw error.message; });
-				// parser.getLexer().on("token", function(r){console.log(r); });
+				parser.getLexer().on("token", function(r){console.log(r); });
 				parser.on("accept", function(ast){ 
 					var type = typeof ast[0].type === "undefined" ? ast[0].head : ast[0].type;
+					type.should.eql("primary-expression");
+
+					var type = typeof ast[0].body[0].type === "undefined" ? ast[0].body[0].head : ast[0].body[0].type;
 					type.should.eql(expected);
+
 					end();
@@ -51,3 +71,2 @@ });
 				try {
-					terminals_pd.startSymbols = [expected];
 					var parser = Parser.CreateWithLexer(terminals_pd, {"path":"./lexical"});
@@ -54,0 +73,0 @@ // parser.getLexer().on("token", function(r){console.log(r); });

examples/php/syntax/primary_expressions.js

@@ -9,7 +9,18 @@ /**
   	"kw":"../lexical/keywords.json",
-    "tokens":"../lexical/tokens.js"
+    "tokens":"../lexical/tokens.js",
+    "literals":"../lexical/literals.js"
   },
   "productions":{
+    "$this":[
+      ["literals.$", "kw.this"]
+    ],
+    "expression-in-parens":[
+      ["literals.(", "primary-expression", "literals.)"]
+    ],
     "primary-expression":[
-      ["tokens.variable-name"]
+      ["$this"],
+      ["tokens.variable-name"],
+      ["tokens.qualified-name"],
+      ["literals.literal"],
+      ["expression-in-parens"],
     ]
@@ -16,0 +27,0 @@ },

examples/re_wrapper.json

@@ -13,3 +13,3 @@ {
     "modules":{
-    	"REX":"examples/re/re.json"
+    	"REX":"re/re.json"
     },
@@ -16,0 +16,0 @@ "symbols": {

lib/lexer.js

@@ -77,2 +77,10 @@ /*
 				}(symbol.matchOnly),
+				"getPriority":function(priority){
+					if(typeof priority === "undefined") {
+						priority = 0;
+					}
+					return function() {
+						return priority;
+					}
+				}(symbol.priority),
 				"removeValue":function(string) {
@@ -136,2 +144,4 @@ return string.replace(this.prefixMatch, "");
 			var longestRule = null;
+			var longestPriority = -1;
+			var tie = false;
 
@@ -144,6 +154,18 @@ for(var r in prefixMatches) {
 					longestRule = rule;
+					longestPriority = rule.getPriority();
+					tie = false;
+				} else if(length == longest) {
+					// see if the tie is broken by priority
+					if(longestPriority === rule.getPriority()) {
+						tie = true;
+					} else if(rule.getPriority() > longestPriority) {
+						longest = length;
+						longestRule = rule;
+						longestPriority = rule.getPriority();
+						tie = false;
+					}
 				}
 			}
 
-			if(longestRule !== null) {
+			if(longestRule !== null && tie !== false) {
 				
@@ -180,3 +202,2 @@ if(longestRule.includeInStream()) {
 			var rule = this.rules[r];
-
 			if(rule.testPrefixWithLookAhead(this.string) || rule.testFull(this.string)) {
@@ -199,2 +220,3 @@ if(rule.testFull(this.string)) {
 
+
 		// If we found prefix matches and no full matches,
@@ -205,2 +227,4 @@ // pick the longest prefix match.
 			var longestRule = null;
+			var longestPriority = -1;
+			var tie = false;
 
@@ -213,2 +237,14 @@ for(var r in prefixMatches) {
 					longestRule = rule;
+					longestPriority = rule.getPriority();
+					tie = false;
+				} else if(length == longest) {
+					// see if the tie is broken by priority
+					if(longestPriority === rule.getPriority()) {
+						tie = true;
+					} else if(rule.getPriority() > longestPriority) {
+						longest = length;
+						longestRule = rule;
+						longestPriority = rule.getPriority();
+						tie = false;
+					}
 				}
@@ -215,0 +251,0 @@ }

lib/parser/lr_parser.js

@@ -49,2 +49,25 @@ /*
 
+LRParserPrototype.bnfString = function() {
+	var str = "";
+	var productions = this.getParserDescription().productions;
+	for(var i in productions) {
+		if(i === constants.augmentation_symbol) {
+			continue ;
+		}
+
+		var prod = productions[i];
+		str += i + " -> \n";
+		for(var p in prod) {
+			var list = prod[p];
+			str += "\t";
+			for(var l in list) {
+				str += list[l] + "  ";
+			}
+			str += "\n";
+		}
+	}
+
+	return str;
+};
+
 // Pretty print
@@ -247,3 +270,3 @@ // Optionally you can provide a tab character.
 	console.debug("[Parser] Importing module (" + modName + ")");
-	
+
 	// Determine the prefix to use while building this module.
@@ -265,3 +288,3 @@ // In most cases it will be the modName + ".", the only exception
 	// deeper down the rabbit hole must be rewritten to reference the correct module.
-	// TODO: Names for modules should be standardized in the parser descriptions to avoid name mismatches allowing modules 
+	// TODO: Names for modules should be standardized in the parser descriptions to avoid name mismatches allowing modules
 	// to be loaded multiple times.
@@ -282,3 +305,3 @@ var dontLoad = [];
 	// provide a function for converting symbol names in this context
-	var processSymbolName = function(currentLevelModules, prefix) { 
+	var processSymbolName = function(currentLevelModules, prefix) {
 		return function(symbol) {
@@ -294,3 +317,3 @@ for(var key in currentLevelModules) {
 			return prefix + symbol;
-		}; 
+		};
 	}(currentLevelModules, prefix);
@@ -394,5 +417,11 @@
 						var type = table_entry[symbol].operation + "-reduce";
-						throw type + " Conflict for symbol " + symbol + " in production " + clause.head;
+
+						if(type === "shift-reduce") {
+							console.log("WARNING: " + type + " Conflict for symbol " + symbol + " in production " + clause.head);
+						} else {
+							throw type + " Conflict for symbol " + symbol + " in production " + clause.head;
+						}
+					} else {
+						table_entry[symbol] = {"operation":"reduce", "state":productionIndex};
 					}
-					table_entry[symbol] = {"operation":"reduce", "state":productionIndex};
 				}
@@ -848,2 +877,3 @@ }
 			var tok = this.token_stack.pop();
+			if(!tok) return this.shift(token);
 			var type = typeof tok.type === "undefined" ? tok.head : tok.type;
@@ -878,3 +908,7 @@
 		}
-		this.token_stack.push({"head":production.head, "body":params});
+
+		// the abandon option will drop this from the stack as we parse them.
+		if(this.getParserDescription().symbols[type].abandon !== true) {
+			this.token_stack.push({"head":production.head, "body":params});
+		}
 		this.emit(production.head, params);
@@ -930,1 +964,2 @@ this.emit("production", production.head, params);
 module.exports.CreateWithLexer = CreateLRParserWithLexer;
+module.exports.prettyPrint = prettyPrint;

package.json

 {
   "name": "js-parse",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "description": "A generic shift-reduce parser for nodejs",
@@ -5,0 +5,0 @@ "main": "index.js",

README.md

@@ -304,2 +304,16 @@
 
+##### abandon
+
+The `abandon` option will cause the matched production to be dropped from the parser
+stack. This means when for all intents and purposes it vanishes from the parse
+tree. I added this option to support really incremental processing.
+
+For example, the `statement_list` defined in [NodePL](https://github.com/kkoch986/nodepl/blob/master/grammars/source.json#L28-L32).
+In that case I had no use for the statements once they were already parsed since
+they were handled by the EventEmitter. What would happen when parsing large files
+with a few thousand statements is it would parse pretty fast but on the file step
+it would have to traverse all the way back to the beginning of the file. This was
+a waste, so instead i drop them from the parse tree and a 10s parse is transformed
+into a 0.5s parse!
+
 ### Productions
@@ -306,0 +320,0 @@

New alerts

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

3157827

increased by2107.1%

Number of package files

176

increased by291.11%

Lines of code

22841

increased by436.55%

Number of lines in readme file

488

increased by2.95%

Worsened metrics

Number of medium supply chain risk alerts

1

increased byInfinity%

No dependency changes