cloud-fan commented on a change in pull request #28802: URL: https://github.com/apache/spark/pull/28802#discussion_r439205389
########## File path: sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/TableIdentifierParserSuite.scala ########## @@ -285,334 +290,86 @@ class TableIdentifierParserSuite extends SparkFunSuite with SQLHelper { "where", "with") - // All the keywords in `docs/sql-keywords.md` are listed below: - val allCandidateKeywords = Set( - "add", - "after", - "all", - "alter", - "analyze", - "and", - "anti", - "any", - "archive", - "array", - "as", - "asc", - "at", - "authorization", - "between", - "both", - "bucket", - "buckets", - "by", - "cache", - "cascade", - "case", - "cast", - "change", - "check", - "clear", - "cluster", - "clustered", - "codegen", - "collate", - "collection", - "column", - "columns", - "comment", - "commit", - "compact", - "compactions", - "compute", - "concatenate", - "constraint", - "cost", - "create", - "cross", - "cube", - "current", - "current_date", - "current_time", - "current_timestamp", - "current_user", - "data", - "database", - "databases", - "day", - "dbproperties", - "defined", - "delete", - "delimited", - "desc", - "describe", - "dfs", - "directories", - "directory", - "distinct", - "distribute", - "div", - "drop", - "else", - "end", - "escape", - "escaped", - "except", - "exchange", - "exists", - "explain", - "export", - "extended", - "external", - "extract", - "false", - "fetch", - "fields", - "fileformat", - "first", - "following", - "for", - "foreign", - "format", - "formatted", - "from", - "full", - "function", - "functions", - "global", - "grant", - "group", - "grouping", - "having", - "hour", - "if", - "ignore", - "import", - "in", - "index", - "indexes", - "inner", - "inpath", - "inputformat", - "insert", - "intersect", - "interval", - "into", - "is", - "items", - "join", - "keys", - "last", - "lateral", - "lazy", - "leading", - "left", - "like", - "limit", - "lines", - "list", - "load", - "local", - "location", - "lock", - "locks", - "logical", - "macro", - "map", - "minus", - "minute", - "month", - "msck", - "namespaces", - "natural", - "no", - "not", - "null", - "nulls", - "of", - "on", - "only", - "option", - "options", - "or", - "order", - "out", - "outer", - "outputformat", - "over", - "overlaps", - "overlay", - "overwrite", - "partition", - "partitioned", - "partitions", - "percent", - "pivot", - "placing", - "position", - "preceding", - "primary", - "principals", - "purge", - "query", - "range", - "recordreader", - "recordwriter", - "recover", - "reduce", - "references", - "refresh", - "rename", - "repair", - "replace", - "reset", - "restrict", - "revoke", - "right", - "rlike", - "role", - "roles", - "rollback", - "rollup", - "row", - "rows", - "schema", - "second", - "select", - "semi", - "separated", - "serde", - "serdeproperties", - "session_user", - "set", - "sets", - "show", - "skewed", - "some", - "sort", - "sorted", - "start", - "statistics", - "stored", - "stratify", - "struct", - "substr", - "substring", - "table", - "tables", - "tablesample", - "tblproperties", - "temporary", - "terminated", - "then", - "to", - "touch", - "trailing", - "transaction", - "transactions", - "transform", - "true", - "truncate", - "type", - "unarchive", - "unbounded", - "uncache", - "union", - "unique", - "unknown", - "unlock", - "unset", - "use", - "user", - "using", - "values", - "view", - "views", - "when", - "where", - "window", - "with", - "year") + private val sqlSyntaxDefs = { + val sqlBasePath = { + val sparkHome = { + assert(sys.props.contains("spark.test.home") || + sys.env.contains("SPARK_HOME"), "spark.test.home or SPARK_HOME is not set.") + sys.props.getOrElse("spark.test.home", sys.env("SPARK_HOME")) + } + java.nio.file.Paths.get(sparkHome, "sql", "catalyst", "src", "main", "antlr4", "org", + "apache", "spark", "sql", "catalyst", "parser", "SqlBase.g4").toFile + } + fileToString(sqlBasePath).split("\n") + } - val reservedKeywordsInAnsiMode = Set( - "all", - "and", - "anti", - "any", - "as", - "authorization", - "both", - "case", - "cast", - "check", - "collate", - "column", - "constraint", - "create", - "cross", - "current_date", - "current_time", - "current_timestamp", - "current_user", - "day", - "distinct", - "else", - "end", - "escape", - "except", - "false", - "fetch", - "for", - "foreign", - "from", - "full", - "grant", - "group", - "having", - "hour", - "in", - "inner", - "intersect", - "into", - "join", - "is", - "leading", - "left", - "minute", - "month", - "natural", - "not", - "null", - "on", - "only", - "or", - "order", - "outer", - "overlaps", - "primary", - "references", - "right", - "select", - "semi", - "session_user", - "minus", - "second", - "some", - "table", - "then", - "to", - "trailing", - "union", - "unique", - "unknown", - "user", - "using", - "when", - "where", - "with", - "year") + private def parseAntlrGrammars(startTag: String, endTag: String) + (f: PartialFunction[String, Option[String]]): Set[String] = { + // We need to map a symbol string to actual literal strings + // in case that they have different strings. + val symbolsToNeedRemap = Map( + "DATABASES" -> Seq("DATABASES", "SCHEMAS"), + "RLIKE" -> Seq("RLIKE", "REGEXP"), + "SETMINUS" -> Seq("MINUS"), + "TEMPORARY" -> Seq("TEMPORARY", "TEMP") + ) + val keywords = new mutable.ArrayBuffer[String] + val default = (_: String) => None + var startTagFound = false + var parseFinished = false + val lineIter = sqlSyntaxDefs.toIterator + while (!parseFinished && lineIter.hasNext) { + val line = lineIter.next() + if (line.trim.startsWith(startTag)) { + startTagFound = true + } else if (line.trim.startsWith(endTag)) { + parseFinished = true + } else if (startTagFound) { + f.applyOrElse(line, default).foreach { symbol => + if (symbolsToNeedRemap.contains(symbol)) { + keywords ++= symbolsToNeedRemap(symbol) + } else { + keywords += symbol + } + } + } + } + assert(keywords.nonEmpty && startTagFound && parseFinished, "cannot extract keywords from " + + s"the `SqlBase.g4` file, so please check if the start/end tags (`$startTag` and `$endTag`) " + + "are placed correctly in the file.") + keywords.map(_.trim.toLowerCase(Locale.ROOT)).toSet + } - val nonReservedKeywordsInAnsiMode = allCandidateKeywords -- reservedKeywordsInAnsiMode + private def parseSyntax(startTag: String, endTag: String): Set[String] = { + val kwDef = """\s*[\|:]\s*([A-Z_]+)\s*""".r + parseAntlrGrammars(startTag, endTag) { + // Parses a pattern, e.g., ` | AFTER` + case kwDef(symbol) => Some(symbol) + } + } + + // All the SQL keywords defined in `SqlBase.g4` + val allCandidateKeywords = { + val kwDef = """([A-Z_]+):.+;""".r + val keywords = parseAntlrGrammars( + "//--SPARK-KEYWORD-LIST-START", "//--SPARK-KEYWORD-LIST-END") { + // Parses a pattern, e.g., `AFTER: 'AFTER';` Review comment: for `KEYWORD: "ABC" | "XYZ"`, it's one keyword or two? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org