[DON'T MERGE] Moves syntax errors to the semantic analysis for supporting both Cypher25 and Cypher5

modify-semantic-analysis.js

@@ -23,9 +23,9 @@ fs.readFile(file, 'utf8', function (err, data) {
     `    cnsa_Main_$callClinit();
     var$1 = var$1.data;
     cnsa_Main_updateSignatureResolver(null);
-    cnsa_Main_analyzeQuery(var$1[0]);
+    cnsa_Main_analyzeQuery(var$1[0], $rt_s(1));
     cnsa_Main_updateSignatureResolver(null);
-    cnsa_Main_analyzeQuery(var$1[0]);`,
+    cnsa_Main_analyzeQuery(var$1[0], $rt_s(2));`,
     `    cnsa_Main_$callClinit();`,
   );
 
@@ -51,7 +51,7 @@ $rt_exports.main([]);
 $rt_exports.updateSignatureResolver = cnsa_Main_updateSignatureResolver;
 
 // Export the analyze function as well
-$rt_exports.semanticAnalysis = $rt_mainStarter(($args) => cnsa_Main_analyzeQuery($args.data[0]));`,
+$rt_exports.semanticAnalysis = $rt_mainStarter(($args) => cnsa_Main_analyzeQuery($args.data[0], $args.data[1]));`,
   );
   fs.writeFile(file, result, 'utf8', function (err) {
     if (err) return console.log(err);

packages/language-server/src/lintWorker.ts

@@ -1,14 +1,12 @@
-import { validateSemantics } from '@neo4j-cypher/language-support';
+import { lintCypherQuery } from '@neo4j-cypher/language-support';
 import workerpool from 'workerpool';
 
-workerpool.worker({ validateSemantics });
+workerpool.worker({ lintCypherQuery });
 
-type LinterArgs = Parameters<typeof validateSemantics>;
+type LinterArgs = Parameters<typeof lintCypherQuery>;
 
-export type LinterTask = workerpool.Promise<
-  ReturnType<typeof validateSemantics>
->;
+export type LinterTask = workerpool.Promise<ReturnType<typeof lintCypherQuery>>;
 
 export type LintWorker = {
-  validateSemantics: (...args: LinterArgs) => LinterTask;
+  lintCypherQuery: (...args: LinterArgs) => LinterTask;
 };

packages/language-server/src/linting.ts

@@ -1,4 +1,3 @@
-import { validateSyntax } from '@neo4j-cypher/language-support';
 import { Neo4jSchemaPoller } from '@neo4j-cypher/schema-poller';
 import debounce from 'lodash.debounce';
 import { join } from 'path';
@@ -28,25 +27,19 @@ async function rawLintDocument(
   }
 
   const dbSchema = neo4j.metadata?.dbSchema ?? {};
-  const syntaxErrors = validateSyntax(query, dbSchema);
-
-  sendDiagnostics(syntaxErrors);
-
-  if (syntaxErrors.length === 0) {
-    try {
-      if (lastSemanticJob !== undefined && !lastSemanticJob.resolved) {
-        void lastSemanticJob.cancel();
-      }
+  try {
+    if (lastSemanticJob !== undefined && !lastSemanticJob.resolved) {
+      void lastSemanticJob.cancel();
+    }
 
-      const proxyWorker = (await pool.proxy()) as unknown as LintWorker;
-      lastSemanticJob = proxyWorker.validateSemantics(query, dbSchema);
-      const result = await lastSemanticJob;
+    const proxyWorker = (await pool.proxy()) as unknown as LintWorker;
+    lastSemanticJob = proxyWorker.lintCypherQuery(query, dbSchema);
+    const result = await lastSemanticJob;
 
-      sendDiagnostics(result);
-    } catch (err) {
-      if (!(err instanceof workerpool.Promise.CancellationError)) {
-        console.error(err);
-      }
+    sendDiagnostics(result);
+  } catch (err) {
+    if (!(err instanceof workerpool.Promise.CancellationError)) {
+      console.error(err);
     }
   }
 }

packages/language-support/package.json

@@ -48,8 +48,9 @@
     "vscode-languageserver-types": "^3.17.3"
   },
   "scripts": {
+    "gen-preparser": "antlr4 -Dlanguage=TypeScript src/PreParser/antlr-grammar/PreParser.g4 -o src/PreParser/generated-preparser/ -Xexact-output-dir",
     "gen-parser": "antlr4 -Dlanguage=TypeScript -visitor src/antlr-grammar/CypherCmdLexer.g4 src/antlr-grammar/CypherCmdParser.g4 -o src/generated-parser/ -Xexact-output-dir",
-    "build": "npm run gen-parser && concurrently 'npm:build-types' 'npm:build-esm' 'npm:build-commonjs'",
+    "build": "npm run gen-preparser && npm run gen-parser && concurrently 'npm:build-types' 'npm:build-esm' 'npm:build-commonjs'",
     "build-types": "tsc --emitDeclarationOnly --outDir dist/types",
     "build-esm": "esbuild ./src/index.ts --bundle --format=esm --sourcemap --outfile=dist/esm/index.mjs",
     "build-commonjs": "esbuild ./src/index.ts --bundle --format=cjs --sourcemap --outfile=dist/cjs/index.cjs",

packages/language-support/src/PreParser/antlr-grammar/PreParser.g4

@@ -0,0 +1,58 @@
+grammar PreParser;
+options { caseInsensitive = true; }
+
+query:
+    cypherVersion? CHAR* EOF;
+
+cypherVersion:
+    cypherFive | cypherTwentyFive;
+
+cypherFive:
+    CYPHER FIVE;
+
+FIVE: '5';
+
+TWENTYFIVE: '25';
+
+cypherTwentyFive:
+    CYPHER TWENTYFIVE;
+
+CYPHER:
+    'CYPHER';
+
+SPACE
+   : ( '\u0009'
+      | '\n' //can't parse this in unicode
+      | '\u000B'
+      | '\u000C'
+      | '\r' //can't parse this in unicode
+      | '\u001C'
+      | '\u001D'
+      | '\u001E'
+      | '\u001F'
+      | '\u0020'
+      | '\u0085'
+      | '\u00A0'
+      | '\u1680'
+      | '\u2000'
+      | '\u2001'
+      | '\u2002'
+      | '\u2003'
+      | '\u2004'
+      | '\u2005'
+      | '\u2006'
+      | '\u2007'
+      | '\u2008'
+      | '\u2009'
+      | '\u200A'
+      | '\u2028'
+      | '\u2029'
+      | '\u202F'
+      | '\u205F'
+      | '\u3000'
+   ) -> channel (HIDDEN)
+   ;
+
+
+CHAR:
+    [\u0000-\uFFFE];

packages/language-support/src/PreParser/generated-preparser/PreParserLexer.ts

@@ -0,0 +1,77 @@
+// Generated from src/PreParser/antlr-grammar/PreParser.g4 by ANTLR 4.13.2
+// noinspection ES6UnusedImports,JSUnusedGlobalSymbols,JSUnusedLocalSymbols
+import {
+	ATN,
+	ATNDeserializer,
+	CharStream,
+	DecisionState, DFA,
+	Lexer,
+	LexerATNSimulator,
+	RuleContext,
+	PredictionContextCache,
+	Token
+} from "antlr4";
+export default class PreParserLexer extends Lexer {
+	public static readonly FIVE = 1;
+	public static readonly TWENTYFIVE = 2;
+	public static readonly CYPHER = 3;
+	public static readonly SPACE = 4;
+	public static readonly CHAR = 5;
+	public static readonly EOF = Token.EOF;
+
+	public static readonly channelNames: string[] = [ "DEFAULT_TOKEN_CHANNEL", "HIDDEN" ];
+	public static readonly literalNames: (string | null)[] = [ null, "'5'", 
+                                                            "'25'", "'CYPHER'" ];
+	public static readonly symbolicNames: (string | null)[] = [ null, "FIVE", 
+                                                             "TWENTYFIVE", 
+                                                             "CYPHER", "SPACE", 
+                                                             "CHAR" ];
+	public static readonly modeNames: string[] = [ "DEFAULT_MODE", ];
+
+	public static readonly ruleNames: string[] = [
+		"FIVE", "TWENTYFIVE", "CYPHER", "SPACE", "CHAR",
+	];
+
+
+	constructor(input: CharStream) {
+		super(input);
+		this._interp = new LexerATNSimulator(this, PreParserLexer._ATN, PreParserLexer.DecisionsToDFA, new PredictionContextCache());
+	}
+
+	public get grammarFileName(): string { return "PreParser.g4"; }
+
+	public get literalNames(): (string | null)[] { return PreParserLexer.literalNames; }
+	public get symbolicNames(): (string | null)[] { return PreParserLexer.symbolicNames; }
+	public get ruleNames(): string[] { return PreParserLexer.ruleNames; }
+
+	public get serializedATN(): number[] { return PreParserLexer._serializedATN; }
+
+	public get channelNames(): string[] { return PreParserLexer.channelNames; }
+
+	public get modeNames(): string[] { return PreParserLexer.modeNames; }
+
+	public static readonly _serializedATN: number[] = [4,0,5,29,6,-1,2,0,7,
+	0,2,1,7,1,2,2,7,2,2,3,7,3,2,4,7,4,1,0,1,0,1,1,1,1,1,1,1,2,1,2,1,2,1,2,1,
+	2,1,2,1,2,1,3,1,3,1,3,1,3,1,4,1,4,0,0,5,1,1,3,2,5,3,7,4,9,5,1,0,8,2,0,67,
+	67,99,99,2,0,89,89,121,121,2,0,80,80,112,112,2,0,72,72,104,104,2,0,69,69,
+	101,101,2,0,82,82,114,114,10,0,9,13,28,32,133,133,160,160,5760,5760,8192,
+	8202,8232,8233,8239,8239,8287,8287,12288,12288,1,0,0,65534,28,0,1,1,0,0,
+	0,0,3,1,0,0,0,0,5,1,0,0,0,0,7,1,0,0,0,0,9,1,0,0,0,1,11,1,0,0,0,3,13,1,0,
+	0,0,5,16,1,0,0,0,7,23,1,0,0,0,9,27,1,0,0,0,11,12,5,53,0,0,12,2,1,0,0,0,
+	13,14,5,50,0,0,14,15,5,53,0,0,15,4,1,0,0,0,16,17,7,0,0,0,17,18,7,1,0,0,
+	18,19,7,2,0,0,19,20,7,3,0,0,20,21,7,4,0,0,21,22,7,5,0,0,22,6,1,0,0,0,23,
+	24,7,6,0,0,24,25,1,0,0,0,25,26,6,3,0,0,26,8,1,0,0,0,27,28,7,7,0,0,28,10,
+	1,0,0,0,1,0,1,0,1,0];
+
+	private static __ATN: ATN;
+	public static get _ATN(): ATN {
+		if (!PreParserLexer.__ATN) {
+			PreParserLexer.__ATN = new ATNDeserializer().deserialize(PreParserLexer._serializedATN);
+		}
+
+		return PreParserLexer.__ATN;
+	}
+
+
+	static DecisionsToDFA = PreParserLexer._ATN.decisionToState.map( (ds: DecisionState, index: number) => new DFA(ds, index) );
+}

packages/language-support/src/PreParser/generated-preparser/PreParserListener.ts

@@ -0,0 +1,58 @@
+// Generated from src/PreParser/antlr-grammar/PreParser.g4 by ANTLR 4.13.2
+
+import {ParseTreeListener} from "antlr4";
+
+
+import { QueryContext } from "./PreParserParser.js";
+import { CypherVersionContext } from "./PreParserParser.js";
+import { CypherFiveContext } from "./PreParserParser.js";
+import { CypherTwentyFiveContext } from "./PreParserParser.js";
+
+
+/**
+ * This interface defines a complete listener for a parse tree produced by
+ * `PreParserParser`.
+ */
+export default class PreParserListener extends ParseTreeListener {
+	/**
+	 * Enter a parse tree produced by `PreParserParser.query`.
+	 * @param ctx the parse tree
+	 */
+	enterQuery?: (ctx: QueryContext) => void;
+	/**
+	 * Exit a parse tree produced by `PreParserParser.query`.
+	 * @param ctx the parse tree
+	 */
+	exitQuery?: (ctx: QueryContext) => void;
+	/**
+	 * Enter a parse tree produced by `PreParserParser.cypherVersion`.
+	 * @param ctx the parse tree
+	 */
+	enterCypherVersion?: (ctx: CypherVersionContext) => void;
+	/**
+	 * Exit a parse tree produced by `PreParserParser.cypherVersion`.
+	 * @param ctx the parse tree
+	 */
+	exitCypherVersion?: (ctx: CypherVersionContext) => void;
+	/**
+	 * Enter a parse tree produced by `PreParserParser.cypherFive`.
+	 * @param ctx the parse tree
+	 */
+	enterCypherFive?: (ctx: CypherFiveContext) => void;
+	/**
+	 * Exit a parse tree produced by `PreParserParser.cypherFive`.
+	 * @param ctx the parse tree
+	 */
+	exitCypherFive?: (ctx: CypherFiveContext) => void;
+	/**
+	 * Enter a parse tree produced by `PreParserParser.cypherTwentyFive`.
+	 * @param ctx the parse tree
+	 */
+	enterCypherTwentyFive?: (ctx: CypherTwentyFiveContext) => void;
+	/**
+	 * Exit a parse tree produced by `PreParserParser.cypherTwentyFive`.
+	 * @param ctx the parse tree
+	 */
+	exitCypherTwentyFive?: (ctx: CypherTwentyFiveContext) => void;
+}
+