package dialect // 函数映射与保留字来自 https://github.com/tobymao/sqlglot // dialects/bigquery.py, dialects/presto.py, dialects/trino.py, generator.py // PrestoConfig Athena/Presto/Trino 方言配置 // 标识符引用：双引号 " (Trino/Presto 标准) var PrestoConfig = &dialectConfig{ funcMap: prestoFuncMap, paramReorder: prestoParamReorder, reservedKeywords: toSet(prestoReservedKeywords), identQuote: `"`, castTypeReplaces: []castTypeReplace{ {"signed", "BIGINT"}, {"unsigned", "BIGINT"}, }, } // BigQueryConfig BigQuery 方言配置 // 标识符引用：反引号 ` (BigQuery 标准) var BigQueryConfig = &dialectConfig{ funcMap: bigQueryFuncMap, paramReorder: bigQueryParamReorder, reservedKeywords: toSet(bigqueryReservedKeywords), identQuote: "`", castTypeReplaces: []castTypeReplace{ {"signed", "INT64"}, {"unsigned", "INT64"}, }, } // MaxComputeConfig MaxCompute (ODPS) 方言配置 // 标识符引用：反引号 ` (Hive 兼容)，函数名与 MySQL 差异较大 var MaxComputeConfig = &dialectConfig{ funcMap: maxComputeFuncMap, paramReorder: maxComputeParamReorder, reservedKeywords: toSet(maxComputeReservedKeywords), identQuote: "`", } // SynapseConfig T-SQL/Synapse Serverless SQL 方言配置 // 标识符引用使用双引号，Synapse 默认 QUOTED_IDENTIFIER ON 时可识别。 var SynapseConfig = &dialectConfig{ funcMap: synapseFuncMap, paramReorder: synapseParamReorder, reservedKeywords: toSet(synapseReservedKeywords), identQuote: `"`, castTypeReplaces: []castTypeReplace{ {"signed", "BIGINT"}, {"unsigned", "BIGINT"}, }, } // prestoParamReorder 目标函数名 -> 参数置换 newArgs[i]=oldArgs[perm[i]] // Presto DATE_DIFF(unit, date1, date2)，输入约定 (date1, date2, unit) var prestoParamReorder = map[string][]int{ "date_diff": {2, 0, 1}, // (d1,d2,unit) -> (unit,d1,d2) } // bigQueryParamReorder 目标函数名 -> 参数置换 // BigQuery FORMAT_TIMESTAMP(format, timestamp[, tz])，输入约定 (timestamp, format[, tz]) // BigQuery PARSE_TIMESTAMP/PARSE_DATE(format, string)，输入约定 (string, format) var bigQueryParamReorder = map[string][]int{ "format_timestamp": {1, 0, 2}, // (ts, fmt[, tz]) -> (fmt, ts[, tz]) "parse_timestamp": {1, 0}, // (str, fmt) -> (fmt, str) "parse_date": {1, 0}, // (str, fmt) -> (fmt, str) } // maxComputeParamReorder MaxCompute 目标函数名 -> 参数置换 // GET_JSON_OBJECT(jsonStr, path) 与 json_extract(json, path) 参数顺序一致 var maxComputeParamReorder = map[string][]int{} var synapseParamReorder = map[string][]int{} // maxComputeFuncMap 逻辑/通用函数 -> MaxCompute 函数（仅保留名称不同的映射，函数名大小写不敏感） // 参考 https://www.alibabacloud.com/help/zh/maxcompute/user-guide/overview 及与 Hive/MySQL/Oracle 内建函数对照表 var maxComputeFuncMap = funcMap{ "json_get": "GET_JSON_OBJECT", "json_extract": "GET_JSON_OBJECT", "json_value": "GET_JSON_OBJECT", "json_extract_scalar": "GET_JSON_OBJECT", "to_timestamp": "FROM_UNIXTIME", "from_unixtime": "FROM_UNIXTIME", "to_unixtime": "UNIX_TIMESTAMP", "current_time": "CURRENT_TIMESTAMP", "now": "GETDATE", "date_format": "TO_CHAR", "date_parse": "TO_DATE", "str_to_date": "TO_DATE", "date_diff": "DATEDIFF", "date_trunc": "DATETRUNC", "regex_match": "REGEXP_CONTAINS", "regexp_like": "REGEXP_CONTAINS", "char_length": "LENGTH", "character_length": "LENGTH", "substring": "SUBSTR", "upper": "TOUPPER", "lower": "TOLOWER", "position": "INSTR", "ifnull": "COALESCE", "approx_distinct": "APPROX_DISTINCT", "approx_count_distinct": "APPROX_DISTINCT", "arbitrary": "ANY_VALUE", "group_concat": "WM_CONCAT", "string_agg": "WM_CONCAT", "array_agg": "COLLECT_LIST", "var_pop": "VARIANCE", "variance": "VAR_SAMP", "stddev_pop": "STDDEV", "stddev": "STDDEV_SAMP", "try_cast": "CAST", "truncate": "TRUNC", "ceiling": "CEIL", "power": "POW", "sha256": "SHA2", } var synapseFuncMap = funcMap{ "ifnull": "coalesce", "char_length": "len", "character_length": "len", "substring": "substring", "any_value": "min", "arbitrary": "min", "approx_distinct": "approx_count_distinct", "approx_count_distinct": "approx_count_distinct", "try_cast": "try_cast", } // maxComputeReservedKeywords MaxCompute 官方保留字 // https://www.alibabacloud.com/help/zh/maxcompute/user-guide/reserved-words-and-keywords var maxComputeReservedKeywords = []string{ "add", "after", "all", "alter", "analyze", "and", "archive", "array", "as", "asc", "before", "between", "bigint", "binary", "blob", "boolean", "both", "bucket", "buckets", "by", "cascade", "case", "cast", "cfile", "change", "cluster", "clustered", "clusterstatus", "collection", "column", "columns", "comment", "compute", "concatenate", "continue", "create", "cross", "current", "cursor", "data", "database", "databases", "date", "datetime", "dbproperties", "decimal", "deferred", "delete", "delimited", "desc", "describe", "directory", "disable", "distinct", "distribute", "div", "double", "drop", "else", "enable", "end", "except", "escaped", "exclusive", "exists", "explain", "export", "extended", "external", "false", "fetch", "fields", "fileformat", "first", "float", "following", "format", "formatted", "from", "full", "function", "functions", "grant", "group", "having", "hold_ddltime", "idxproperties", "if", "import", "in", "index", "indexes", "inputdriver", "inputformat", "insert", "int", "intersect", "into", "is", "items", "join", "keys", "lateral", "left", "lifecycle", "like", "limit", "lines", "load", "local", "location", "lock", "locks", "long", "map", "mapjoin", "materialized", "minus", "msck", "no_drop", "not", "null", "of", "offline", "offset", "on", "option", "or", "order", "out", "outer", "outputdriver", "outputformat", "over", "overwrite", "partition", "partitioned", "partitionproperties", "partitions", "percent", "plus", "preceding", "preserve", "procedure", "purge", "range", "rcfile", "read", "readonly", "reads", "rebuild", "recordreader", "recordwriter", "reduce", "regexp", "rename", "repair", "replace", "restrict", "revoke", "right", "rlike", "row", "rows", "schema", "schemas", "select", "semi", "sequencefile", "serde", "serdeproperties", "set", "shared", "show", "show_database", "smallint", "sort", "sorted", "ssl", "statistics", "status", "stored", "streamtable", "string", "struct", "table", "tables", "tablesample", "tblproperties", "temporary", "terminated", "textfile", "then", "timestamp", "tinyint", "to", "touch", "transform", "trigger", "true", "type", "unarchive", "unbounded", "undo", "union", "uniontype", "uniquejoin", "unlock", "unsigned", "update", "use", "using", "utc", "utc_timestamp", "view", "when", "where", "while", } func toSet(ss []string) map[string]bool { m := make(map[string]bool, len(ss)) for _, s := range ss { m[s] = true } return m } // prestoFuncMap 逻辑/通用函数 -> Presto/Trino 函数（仅保留名称不同的映射，函数名大小写不敏感） var prestoFuncMap = funcMap{ "json_get": "json_extract", "json_value": "json_extract_scalar", "to_timestamp": "from_unixtime", "unix_timestamp": "to_unixtime", "to_unixtime": "to_unixtime", "str_to_date": "date_parse", "regex_match": "regexp_like", "char_length": "length", "character_length": "length", "position": "strpos", "instr": "strpos", "ifnull": "coalesce", "any_value": "arbitrary", "group_concat": "array_join", "string_agg": "array_join", "variance": "var_samp", "stddev": "stddev_samp", "try_cast": "try_cast", "array_length": "cardinality", "array_contains": "contains", } // bigQueryFuncMap 逻辑/通用函数 -> BigQuery 函数（仅保留名称不同的映射，函数名大小写不敏感） var bigQueryFuncMap = funcMap{ "json_get": "JSON_VALUE", "json_extract": "JSON_EXTRACT", "json_extract_scalar": "JSON_VALUE", "to_timestamp": "TIMESTAMP_SECONDS", "from_unixtime": "TIMESTAMP_SECONDS", "unix_timestamp": "UNIX_SECONDS", "to_unixtime": "UNIX_SECONDS", "date_format": "FORMAT_TIMESTAMP", "date_parse": "PARSE_TIMESTAMP", "str_to_date": "PARSE_DATE", "regex_match": "REGEXP_CONTAINS", "regexp_like": "REGEXP_CONTAINS", "char_length": "LENGTH", "character_length": "LENGTH", "substring": "SUBSTR", "position": "STRPOS", "ifnull": "COALESCE", "approx_distinct": "APPROX_COUNT_DISTINCT", "approx_count_distinct": "APPROX_COUNT_DISTINCT", "arbitrary": "ANY_VALUE", "group_concat": "STRING_AGG", "string_agg": "STRING_AGG", "variance": "VAR_SAMP", "stddev_pop": "STDDEV_POP", "stddev": "STDDEV_SAMP", "countif": "COUNTIF", "try_cast": "SAFE_CAST", "cardinality": "ARRAY_LENGTH", "contains": "CONTAINS_SUBSTR", "slice": "ARRAY_SLICE", "array_join": "ARRAY_TO_STRING", } // prestoReservedKeywords 来自 sqlglot dialects/presto.py RESERVED_KEYWORDS var prestoReservedKeywords = []string{ "alter", "and", "as", "between", "by", "case", "cast", "constraint", "create", "cross", "current_time", "current_timestamp", "deallocate", "delete", "describe", "distinct", "drop", "else", "end", "escape", "except", "execute", "exists", "extract", "false", "for", "from", "full", "group", "having", "in", "inner", "insert", "intersect", "into", "is", "join", "left", "like", "natural", "not", "null", "on", "or", "order", "outer", "prepare", "right", "select", "table", "then", "true", "union", "using", "values", "when", "where", "with", "date", "time", "timestamp", "interval", "limit", "offset", } // bigqueryReservedKeywords 来自 sqlglot dialects/bigquery.py RESERVED_KEYWORDS var bigqueryReservedKeywords = []string{ "all", "and", "any", "array", "as", "asc", "assert_rows_modified", "at", "between", "by", "case", "cast", "collate", "contains", "create", "cross", "cube", "current", "default", "define", "desc", "distinct", "else", "end", "enum", "escape", "except", "exclude", "exists", "extract", "false", "fetch", "following", "for", "from", "full", "group", "grouping", "groups", "hash", "having", "if", "ignore", "in", "inner", "intersect", "interval", "into", "is", "join", "lateral", "left", "like", "limit", "lookup", "merge", "natural", "new", "no", "not", "null", "nulls", "of", "on", "or", "order", "outer", "over", "partition", "preceding", "proto", "qualify", "range", "recursive", "respect", "right", "rollup", "rows", "select", "set", "some", "struct", "tablesample", "then", "to", "treat", "true", "unbounded", "union", "unnest", "using", "when", "where", "window", "with", "within", "date", "time", "timestamp", "offset", } var synapseReservedKeywords = []string{ "add", "all", "alter", "and", "any", "as", "asc", "authorization", "backup", "begin", "between", "break", "browse", "bulk", "by", "cascade", "case", "check", "checkpoint", "close", "clustered", "coalesce", "collate", "column", "commit", "compute", "constraint", "contains", "continue", "convert", "create", "cross", "current", "current_date", "current_time", "current_timestamp", "current_user", "cursor", "database", "date", "dbcc", "deallocate", "declare", "default", "delete", "deny", "desc", "distinct", "distributed", "double", "drop", "else", "end", "errlvl", "escape", "except", "exec", "execute", "exists", "exit", "external", "fetch", "file", "fillfactor", "for", "foreign", "from", "full", "function", "goto", "grant", "group", "having", "holdlock", "identity", "if", "in", "index", "inner", "insert", "intersect", "into", "is", "join", "key", "kill", "left", "like", "lineno", "load", "merge", "national", "nocheck", "nonclustered", "not", "null", "nullif", "of", "off", "offset", "on", "open", "opendatasource", "openquery", "openrowset", "openxml", "option", "or", "order", "outer", "over", "percent", "pivot", "plan", "precision", "primary", "print", "proc", "procedure", "public", "raiserror", "read", "readtext", "reconfigure", "references", "replication", "restore", "restrict", "return", "revert", "revoke", "right", "rollback", "row", "rows", "rule", "save", "schema", "select", "session_user", "set", "setuser", "shutdown", "some", "statistics", "system_user", "table", "textsize", "then", "time", "timestamp", "to", "top", "tran", "transaction", "trigger", "truncate", "try_convert", "tsequal", "union", "unique", "unpivot", "update", "updatetext", "use", "user", "values", "varying", "view", "waitfor", "when", "where", "while", "with", "within", "writetext", }