@jacobknightley/fabric-format 0.0.1

package/dist/formatters/sparksql/generated/builtinFunctions.d.ts

@@ -0,0 +1,8 @@
+/**
+ * Auto-generated list of Spark SQL built-in functions.
+ * Source: https://raw.githubusercontent.com/apache/spark/master/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
+ * Generated from sql-expression-schema.md by ExpressionsSchemaSuite
+ *
+ * DO NOT EDIT - regenerate with: python scripts/build_antlr_js.py
+ */
+export declare const SPARK_BUILTIN_FUNCTIONS: ReadonlySet<string>;

package/dist/formatters/sparksql/generated/builtinFunctions.js

@@ -0,0 +1,510 @@
+/**
+ * Auto-generated list of Spark SQL built-in functions.
+ * Source: https://raw.githubusercontent.com/apache/spark/master/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
+ * Generated from sql-expression-schema.md by ExpressionsSchemaSuite
+ *
+ * DO NOT EDIT - regenerate with: python scripts/build_antlr_js.py
+ */
+export const SPARK_BUILTIN_FUNCTIONS = new Set([
+    "abs",
+    "acos",
+    "acosh",
+    "add_months",
+    "aes_decrypt",
+    "aes_encrypt",
+    "aggregate",
+    "and",
+    "any",
+    "any_value",
+    "approx_count_distinct",
+    "approx_percentile",
+    "approx_top_k",
+    "approx_top_k_accumulate",
+    "approx_top_k_combine",
+    "approx_top_k_estimate",
+    "array",
+    "array_agg",
+    "array_append",
+    "array_compact",
+    "array_contains",
+    "array_distinct",
+    "array_except",
+    "array_insert",
+    "array_intersect",
+    "array_join",
+    "array_max",
+    "array_min",
+    "array_position",
+    "array_prepend",
+    "array_remove",
+    "array_repeat",
+    "array_size",
+    "array_sort",
+    "array_union",
+    "arrays_overlap",
+    "arrays_zip",
+    "ascii",
+    "asin",
+    "asinh",
+    "assert_true",
+    "atan",
+    "atan2",
+    "atanh",
+    "avg",
+    "base64",
+    "between",
+    "bigint",
+    "bin",
+    "binary",
+    "bit_and",
+    "bit_count",
+    "bit_get",
+    "bit_length",
+    "bit_or",
+    "bit_xor",
+    "bitmap_and_agg",
+    "bitmap_bit_position",
+    "bitmap_bucket_number",
+    "bitmap_construct_agg",
+    "bitmap_count",
+    "bitmap_or_agg",
+    "bool_and",
+    "bool_or",
+    "boolean",
+    "bround",
+    "btrim",
+    "cardinality",
+    "cast",
+    "cbrt",
+    "ceil",
+    "ceiling",
+    "char",
+    "char_length",
+    "character_length",
+    "chr",
+    "coalesce",
+    "collate",
+    "collation",
+    "collect_list",
+    "collect_set",
+    "concat",
+    "concat_ws",
+    "contains",
+    "conv",
+    "convert_timezone",
+    "corr",
+    "cos",
+    "cosh",
+    "cot",
+    "count",
+    "count_if",
+    "count_min_sketch",
+    "covar_pop",
+    "covar_samp",
+    "crc32",
+    "csc",
+    "cume_dist",
+    "curdate",
+    "current_catalog",
+    "current_database",
+    "current_date",
+    "current_schema",
+    "current_time",
+    "current_timestamp",
+    "current_timezone",
+    "current_user",
+    "date",
+    "date_add",
+    "date_diff",
+    "date_format",
+    "date_from_unix_date",
+    "date_part",
+    "date_sub",
+    "date_trunc",
+    "dateadd",
+    "datediff",
+    "datepart",
+    "day",
+    "dayname",
+    "dayofmonth",
+    "dayofweek",
+    "dayofyear",
+    "decimal",
+    "decode",
+    "degrees",
+    "dense_rank",
+    "div",
+    "double",
+    "e",
+    "element_at",
+    "elt",
+    "encode",
+    "endswith",
+    "equal_null",
+    "every",
+    "exists",
+    "exp",
+    "explode",
+    "explode_outer",
+    "expm1",
+    "extract",
+    "factorial",
+    "filter",
+    "find_in_set",
+    "first",
+    "first_value",
+    "flatten",
+    "float",
+    "floor",
+    "forall",
+    "format_number",
+    "format_string",
+    "from_csv",
+    "from_json",
+    "from_unixtime",
+    "from_utc_timestamp",
+    "from_xml",
+    "get",
+    "get_json_object",
+    "getbit",
+    "greatest",
+    "grouping",
+    "grouping_id",
+    "hash",
+    "hex",
+    "histogram_numeric",
+    "hll_sketch_agg",
+    "hll_sketch_estimate",
+    "hll_union",
+    "hll_union_agg",
+    "hour",
+    "hypot",
+    "if",
+    "ifnull",
+    "ilike",
+    "in",
+    "initcap",
+    "inline",
+    "inline_outer",
+    "input_file_block_length",
+    "input_file_block_start",
+    "input_file_name",
+    "instr",
+    "int",
+    "is_valid_utf8",
+    "is_variant_null",
+    "isnan",
+    "isnotnull",
+    "isnull",
+    "java_method",
+    "json_array_length",
+    "json_object_keys",
+    "json_tuple",
+    "kll_sketch_agg_bigint",
+    "kll_sketch_agg_double",
+    "kll_sketch_agg_float",
+    "kll_sketch_get_n_bigint",
+    "kll_sketch_get_n_double",
+    "kll_sketch_get_n_float",
+    "kll_sketch_get_quantile_bigint",
+    "kll_sketch_get_quantile_double",
+    "kll_sketch_get_quantile_float",
+    "kll_sketch_get_rank_bigint",
+    "kll_sketch_get_rank_double",
+    "kll_sketch_get_rank_float",
+    "kll_sketch_merge_bigint",
+    "kll_sketch_merge_double",
+    "kll_sketch_merge_float",
+    "kll_sketch_to_string_bigint",
+    "kll_sketch_to_string_double",
+    "kll_sketch_to_string_float",
+    "kurtosis",
+    "lag",
+    "last",
+    "last_day",
+    "last_value",
+    "lcase",
+    "lead",
+    "least",
+    "left",
+    "len",
+    "length",
+    "levenshtein",
+    "like",
+    "listagg",
+    "ln",
+    "localtimestamp",
+    "locate",
+    "log",
+    "log10",
+    "log1p",
+    "log2",
+    "lower",
+    "lpad",
+    "ltrim",
+    "luhn_check",
+    "make_date",
+    "make_dt_interval",
+    "make_interval",
+    "make_time",
+    "make_timestamp",
+    "make_timestamp_ltz",
+    "make_timestamp_ntz",
+    "make_valid_utf8",
+    "make_ym_interval",
+    "map",
+    "map_concat",
+    "map_contains_key",
+    "map_entries",
+    "map_filter",
+    "map_from_arrays",
+    "map_from_entries",
+    "map_keys",
+    "map_values",
+    "map_zip_with",
+    "mask",
+    "max",
+    "max_by",
+    "md5",
+    "mean",
+    "median",
+    "min",
+    "min_by",
+    "minute",
+    "mod",
+    "mode",
+    "monotonically_increasing_id",
+    "month",
+    "monthname",
+    "months_between",
+    "named_struct",
+    "nanvl",
+    "negative",
+    "next_day",
+    "not",
+    "now",
+    "nth_value",
+    "ntile",
+    "nullif",
+    "nullifzero",
+    "nvl",
+    "nvl2",
+    "octet_length",
+    "or",
+    "overlay",
+    "parse_json",
+    "parse_url",
+    "percent_rank",
+    "percentile",
+    "percentile_approx",
+    "percentile_cont",
+    "percentile_disc",
+    "pi",
+    "pmod",
+    "posexplode",
+    "posexplode_outer",
+    "position",
+    "positive",
+    "pow",
+    "power",
+    "printf",
+    "quarter",
+    "quote",
+    "radians",
+    "raise_error",
+    "rand",
+    "randn",
+    "random",
+    "randstr",
+    "rank",
+    "reduce",
+    "reflect",
+    "regexp",
+    "regexp_count",
+    "regexp_extract",
+    "regexp_extract_all",
+    "regexp_instr",
+    "regexp_like",
+    "regexp_replace",
+    "regexp_substr",
+    "regr_avgx",
+    "regr_avgy",
+    "regr_count",
+    "regr_intercept",
+    "regr_r2",
+    "regr_slope",
+    "regr_sxx",
+    "regr_sxy",
+    "regr_syy",
+    "repeat",
+    "replace",
+    "reverse",
+    "right",
+    "rint",
+    "rlike",
+    "round",
+    "row_number",
+    "rpad",
+    "rtrim",
+    "schema_of_csv",
+    "schema_of_json",
+    "schema_of_variant",
+    "schema_of_variant_agg",
+    "schema_of_xml",
+    "sec",
+    "second",
+    "sentences",
+    "sequence",
+    "session_user",
+    "session_window",
+    "sha",
+    "sha1",
+    "sha2",
+    "shiftleft",
+    "shiftright",
+    "shiftrightunsigned",
+    "shuffle",
+    "sign",
+    "signum",
+    "sin",
+    "sinh",
+    "size",
+    "skewness",
+    "slice",
+    "smallint",
+    "some",
+    "sort_array",
+    "soundex",
+    "space",
+    "spark_partition_id",
+    "split",
+    "split_part",
+    "sqrt",
+    "st_asbinary",
+    "st_geogfromwkb",
+    "st_geomfromwkb",
+    "st_setsrid",
+    "st_srid",
+    "stack",
+    "startswith",
+    "std",
+    "stddev",
+    "stddev_pop",
+    "stddev_samp",
+    "str_to_map",
+    "string",
+    "string_agg",
+    "struct",
+    "substr",
+    "substring",
+    "substring_index",
+    "sum",
+    "tan",
+    "tanh",
+    "theta_difference",
+    "theta_intersection",
+    "theta_intersection_agg",
+    "theta_sketch_agg",
+    "theta_sketch_estimate",
+    "theta_union",
+    "theta_union_agg",
+    "time",
+    "time_diff",
+    "time_from_micros",
+    "time_from_millis",
+    "time_from_seconds",
+    "time_to_micros",
+    "time_to_millis",
+    "time_to_seconds",
+    "time_trunc",
+    "timestamp",
+    "timestamp_micros",
+    "timestamp_millis",
+    "timestamp_seconds",
+    "tinyint",
+    "to_binary",
+    "to_char",
+    "to_csv",
+    "to_date",
+    "to_json",
+    "to_number",
+    "to_time",
+    "to_timestamp",
+    "to_timestamp_ltz",
+    "to_timestamp_ntz",
+    "to_unix_timestamp",
+    "to_utc_timestamp",
+    "to_varchar",
+    "to_variant_object",
+    "to_xml",
+    "transform",
+    "transform_keys",
+    "transform_values",
+    "translate",
+    "trim",
+    "trunc",
+    "try_add",
+    "try_aes_decrypt",
+    "try_avg",
+    "try_divide",
+    "try_element_at",
+    "try_make_interval",
+    "try_make_timestamp",
+    "try_make_timestamp_ltz",
+    "try_make_timestamp_ntz",
+    "try_mod",
+    "try_multiply",
+    "try_parse_json",
+    "try_parse_url",
+    "try_reflect",
+    "try_subtract",
+    "try_sum",
+    "try_to_binary",
+    "try_to_date",
+    "try_to_number",
+    "try_to_time",
+    "try_to_timestamp",
+    "try_url_decode",
+    "try_validate_utf8",
+    "try_variant_get",
+    "typeof",
+    "ucase",
+    "unbase64",
+    "unhex",
+    "uniform",
+    "unix_date",
+    "unix_micros",
+    "unix_millis",
+    "unix_seconds",
+    "unix_timestamp",
+    "upper",
+    "url_decode",
+    "url_encode",
+    "user",
+    "uuid",
+    "validate_utf8",
+    "var_pop",
+    "var_samp",
+    "variance",
+    "variant_get",
+    "version",
+    "weekday",
+    "weekofyear",
+    "when",
+    "width_bucket",
+    "window",
+    "window_time",
+    "xpath",
+    "xpath_boolean",
+    "xpath_double",
+    "xpath_float",
+    "xpath_int",
+    "xpath_long",
+    "xpath_number",
+    "xpath_short",
+    "xpath_string",
+    "xxhash64",
+    "year",
+    "zeroifnull",
+    "zip_with",
+]);

package/dist/formatters/sparksql/index.d.ts

@@ -0,0 +1,11 @@
+/**
+ * Spark SQL Formatter - Module Exports
+ *
+ * This is the 100% grammar-driven SQL formatter for Apache Spark SQL.
+ * All modules in this directory work together to format SQL.
+ */
+export { formatSql, needsFormatting } from './formatter.js';
+export { SqlFormatter, getSqlFormatter, isSqlCode } from './sql-formatter.js';
+export { hasFormatOff, detectCollapseDirectives, hasCollapseDirective, isFmtInlineComment, type FormatDirectiveInfo, type ForceInlineRange, } from './fmt-detector.js';
+export { MAX_LINE_WIDTH } from './constants.js';
+export type { AnalyzerResult, FormattingState, MultiArgFunctionInfo, WindowDefInfo, TokenContext, PendingComment, ExpandedFunction, ExpandedWindow, ExpandedPivot, PivotInfo, InListInfo, SimpleQueryInfo, NestedFunctionInfo, } from './types.js';

package/dist/formatters/sparksql/index.js

@@ -0,0 +1,22 @@
+/**
+ * Spark SQL Formatter - Module Exports
+ *
+ * This is the 100% grammar-driven SQL formatter for Apache Spark SQL.
+ * All modules in this directory work together to format SQL.
+ */
+// ============================================================================
+// PUBLIC API
+// ============================================================================
+export { formatSql, needsFormatting } from './formatter.js';
+// ============================================================================
+// FORMATTER CLASS (LanguageFormatter interface)
+// ============================================================================
+export { SqlFormatter, getSqlFormatter, isSqlCode } from './sql-formatter.js';
+// ============================================================================
+// FORMAT DIRECTIVES
+// ============================================================================
+export { hasFormatOff, detectCollapseDirectives, hasCollapseDirective, isFmtInlineComment, } from './fmt-detector.js';
+// ============================================================================
+// CONSTANTS
+// ============================================================================
+export { MAX_LINE_WIDTH } from './constants.js';

package/dist/formatters/sparksql/output-builder.d.ts

@@ -0,0 +1,89 @@
+/**
+ * Output Builder - Token Output and Column Tracking
+ *
+ * This module handles the construction of the formatted output string.
+ * It tracks column position for line-width decisions and provides
+ * utilities for spacing and newline insertion.
+ */
+import type { PendingComment } from './types.js';
+/**
+ * Builds the formatted output string with column tracking.
+ */
+export declare class OutputBuilder {
+    private output;
+    private currentColumn;
+    /**
+     * Push text to output and update column tracking.
+     */
+    push(text: string): void;
+    /**
+     * Get the current column position.
+     */
+    getColumn(): number;
+    /**
+     * Get the last character that was output.
+     */
+    getLastChar(): string;
+    /**
+     * Check if output is empty.
+     */
+    isEmpty(): boolean;
+    /**
+     * Check if the last output ends with a newline.
+     */
+    endsWithNewline(): boolean;
+    /**
+     * Get the final formatted string.
+     */
+    toString(): string;
+    /**
+     * Update column tracking based on text content.
+     */
+    private updateColumn;
+    /**
+     * Add a space if needed before the next token.
+     */
+    addSpaceIfNeeded(): void;
+    /**
+     * Ensure we're at the start of a new line.
+     */
+    ensureNewline(): void;
+}
+/**
+ * Outputs pending comments with proper formatting.
+ */
+export declare function outputComments(builder: OutputBuilder, comments: PendingComment[], addSpaceBefore?: boolean): {
+    outputAny: boolean;
+    lastWasMultilineBlock: boolean;
+};
+/**
+ * Determines if a space should be skipped before the current token.
+ */
+export declare function shouldSkipSpace(builder: OutputBuilder, text: string, context: {
+    prevWasFunctionName: boolean;
+    prevWasBuiltInFunctionKeyword: boolean;
+    insideParens: number;
+    justOutputCommaFirstStyle: boolean;
+    justOutputMultiArgFunctionNewline: boolean;
+    justOutputWindowNewline: boolean;
+    justOutputInListWrapNewline: boolean;
+    afterWhereKeyword: boolean;
+    afterHavingKeyword: boolean;
+    prevTokenWasUnaryOperator: boolean;
+    currentTokenIsUnaryOperator: boolean;
+    isLateralViewComma: boolean;
+    prevIsDoubleColon: boolean;
+    prevTokenText: string;
+    currentTokenIsStringLiteral: boolean;
+    prevWasDotToken: boolean;
+    complexTypeDepth: number;
+}): boolean;
+/**
+ * Determines if a comma-space should be added.
+ */
+export declare function shouldAddCommaSpace(builder: OutputBuilder, insideParens: number, justOutputCommaFirstStyle: boolean): boolean;
+/**
+ * Format hint content: uppercase hint names, preserve table names.
+ * Example: "broadcast(t1), merge(t2)" → "BROADCAST(t1), MERGE(t2)"
+ */
+export declare function formatHintContent(content: string): string;