gff-nostream 4.0.0 → 5.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -77,25 +77,36 @@ to its parent (or kept as a top-level item) independently.
77
77
  Synchronously parse a GFF3 string and return an array of features. Comments,
78
78
  directives, and `##FASTA` sections are ignored.
79
79
 
80
- ### `parseRecords(records: LineRecord[]): GffFeature[]`
80
+ ### `parseRecords<R>(records: readonly R[]): ParsedRecord<R>[]`
81
81
 
82
- Parse an array of `LineRecord` objects. Useful when managing raw line data
83
- directly (e.g. from a tabix-indexed file with byte offsets).
82
+ Parse an array of records wrapping raw GFF3 lines. Useful when managing raw line
83
+ data directly (e.g. from a tabix-indexed file). Each top-level feature is
84
+ returned paired with the record it came from, so a caller can attach its own
85
+ stable id (a byte offset, a hash, …) without the parser stamping anything onto
86
+ the feature. Records may carry extra fields (`R` is inferred), which pass
87
+ through untouched on `record`.
88
+
89
+ ```ts
90
+ const features = parseRecords(
91
+ lines.map(line => ({ line, offset })),
92
+ ).map(({ feature, record }) => ({ ...feature, id: record.offset }))
93
+ ```
84
94
 
85
95
  ### `extractType(line: string): string`
86
96
 
87
97
  Extract the feature type (GFF3 column 3) from a raw line without fully splitting
88
98
  it.
89
99
 
90
- ### `LineRecord`
100
+ ### `LineRecord` / `ParsedRecord`
91
101
 
92
102
  ```ts
93
103
  interface LineRecord {
94
104
  line: string
95
- hasEscapes: boolean // set true when line contains '%' to enable URL-decoding
96
- lineHash?: string | number // propagated to the feature's _lineHash field
97
- start?: number // byte offset passthrough (not used by the parser)
98
- end?: number // byte offset passthrough (not used by the parser)
105
+ }
106
+
107
+ interface ParsedRecord<R extends LineRecord = LineRecord> {
108
+ feature: GffFeature
109
+ record: R // the input record this top-level feature was parsed from
99
110
  }
100
111
  ```
101
112
 
package/dist/api.d.ts CHANGED
@@ -1,16 +1,16 @@
1
1
  import type { GffFeature } from './util.ts';
2
- interface ParseInput {
2
+ export interface LineRecord {
3
+ /** Raw GFF3 feature line */
3
4
  line: string;
4
- lineHash?: string | number;
5
- hasEscapes: boolean;
6
5
  }
7
- export interface LineRecord extends ParseInput {
8
- /** Genomic start coordinate from the tabix index (1-based) */
9
- start: number;
10
- /** Genomic end coordinate from the tabix index */
11
- end: number;
12
- /** GFF3 feature type (column 3) */
13
- type: string;
6
+ /**
7
+ * A top-level parsed feature paired with the input record it came from. The
8
+ * parser stamps no identity onto the feature itself; callers that need a stable
9
+ * per-feature id (e.g. from a tabix byte offset) read it off their own `record`.
10
+ */
11
+ export interface ParsedRecord<R extends LineRecord = LineRecord> {
12
+ feature: GffFeature;
13
+ record: R;
14
14
  }
15
15
  /** Extract the GFF3 feature type (column 3) from a raw line without a full split. */
16
16
  export declare function extractType(line: string): string;
@@ -23,11 +23,13 @@ export declare function extractType(line: string): string;
23
23
  */
24
24
  export declare function parseStringSync(str: string): GffFeature[];
25
25
  /**
26
- * Parse an array of LineRecord objects containing raw GFF3 lines.
27
- * Supports parent/child relationships via subfeatures.
26
+ * Parse an array of records wrapping raw GFF3 lines, resolving parent/child
27
+ * relationships into `subfeatures`. Returns each top-level feature paired with
28
+ * the record it came from, so callers can attach their own identity (e.g. a
29
+ * byte offset) without the parser stamping anything onto the feature.
28
30
  *
29
- * @param records - Array of LineRecord objects with raw line and metadata
30
- * @returns array of parsed features
31
+ * @param records - Array of records, each carrying a raw GFF3 `line`
32
+ * @returns top-level features, each paired with its originating record
31
33
  */
32
- export declare function parseRecords(records: ParseInput[]): GffFeature[];
34
+ export declare function parseRecords<R extends LineRecord>(records: readonly R[]): ParsedRecord<R>[];
33
35
  export type { GffFeature } from './util.ts';
package/dist/api.js CHANGED
@@ -36,6 +36,42 @@ function toStringArray(value) {
36
36
  }
37
37
  return typeof value === 'string' ? [value] : [];
38
38
  }
39
+ /**
40
+ * Register a feature's ID and attach it to its parent(s), building the
41
+ * subfeature tree in `byId`/`orphans`. Returns true when the feature is
42
+ * top-level (has no Parent) and the caller should collect it.
43
+ */
44
+ function linkFeature(feature, byId, orphans) {
45
+ const id = firstString(feature.id);
46
+ const parents = toStringArray(feature.parent);
47
+ // Register the id only the first time it is seen. Continuation lines
48
+ // (multi-location features such as a CDS spanning several segments share one
49
+ // ID across lines) skip registration but must still be attached to their
50
+ // parent below, so this is independent of the parent handling.
51
+ if (id && !byId.has(id)) {
52
+ byId.set(id, feature);
53
+ const waiting = orphans.get(id);
54
+ if (waiting) {
55
+ for (const w of waiting) {
56
+ feature.subfeatures.push(w);
57
+ }
58
+ orphans.delete(id);
59
+ }
60
+ }
61
+ for (const parentId of parents) {
62
+ const parentFeature = byId.get(parentId);
63
+ if (parentFeature) {
64
+ parentFeature.subfeatures.push(feature);
65
+ }
66
+ else {
67
+ appendOrphan(orphans, parentId, feature);
68
+ }
69
+ }
70
+ // Every line of a top-level discontinuous feature (e.g. cDNA_match spanning
71
+ // several segments under one shared ID, with no Parent) is its own top-level
72
+ // item, so this is independent of whether the id was just registered.
73
+ return parents.length === 0;
74
+ }
39
75
  /**
40
76
  * Synchronously parse a string containing GFF3 and return an array of the
41
77
  * parsed features. Comments, directives, and `##FASTA` sections are ignored.
@@ -44,72 +80,39 @@ function toStringArray(value) {
44
80
  * @returns array of parsed features
45
81
  */
46
82
  function parseStringSync(str) {
47
- return parseRecords(stringToRecords(str));
48
- }
49
- function stringToRecords(str) {
50
- const lines = str.split(/\r?\n/);
51
- const records = [];
52
- for (const line of lines) {
83
+ const items = [];
84
+ const byId = new Map();
85
+ const orphans = new Map();
86
+ for (const line of str.split(/\r?\n/)) {
53
87
  if (line.startsWith('##FASTA') || line.startsWith('>')) {
54
88
  break;
55
89
  }
56
- if (line.length === 0 || line.startsWith('#')) {
57
- continue;
90
+ if (line.length !== 0 && !line.startsWith('#')) {
91
+ const feature = (0, util_ts_1.parseFeature)(line);
92
+ if (linkFeature(feature, byId, orphans)) {
93
+ items.push(feature);
94
+ }
58
95
  }
59
- records.push({
60
- line,
61
- hasEscapes: line.includes('%'),
62
- });
63
96
  }
64
- return records;
97
+ return items;
65
98
  }
66
99
  /**
67
- * Parse an array of LineRecord objects containing raw GFF3 lines.
68
- * Supports parent/child relationships via subfeatures.
100
+ * Parse an array of records wrapping raw GFF3 lines, resolving parent/child
101
+ * relationships into `subfeatures`. Returns each top-level feature paired with
102
+ * the record it came from, so callers can attach their own identity (e.g. a
103
+ * byte offset) without the parser stamping anything onto the feature.
69
104
  *
70
- * @param records - Array of LineRecord objects with raw line and metadata
71
- * @returns array of parsed features
105
+ * @param records - Array of records, each carrying a raw GFF3 `line`
106
+ * @returns top-level features, each paired with its originating record
72
107
  */
73
108
  function parseRecords(records) {
74
109
  const items = [];
75
110
  const byId = new Map();
76
111
  const orphans = new Map();
77
112
  for (const record of records) {
78
- const feature = (0, util_ts_1.parseFeature)(record.line, record.hasEscapes);
79
- if (record.lineHash !== undefined) {
80
- feature._lineHash = String(record.lineHash);
81
- }
82
- const id = firstString(feature.id);
83
- const parents = toStringArray(feature.parent);
84
- // A parentless line is a top-level item. Every line of a top-level
85
- // discontinuous feature (e.g. cDNA_match/EST_match spanning several
86
- // segments under one shared ID, with no Parent) is its own top-level
87
- // item, so push regardless of whether the id is already registered.
88
- if (parents.length === 0) {
89
- items.push(feature);
90
- }
91
- // Register the id only the first time it is seen. Continuation lines
92
- // (multi-location features such as a CDS spanning several segments share
93
- // one ID across lines) skip registration but must still be attached to
94
- // their parent below, so this is independent of the parent handling.
95
- if (id && !byId.has(id)) {
96
- byId.set(id, feature);
97
- const waiting = orphans.get(id);
98
- if (waiting) {
99
- for (const w of waiting) {
100
- feature.subfeatures.push(w);
101
- }
102
- orphans.delete(id);
103
- }
104
- }
105
- for (const parentId of parents) {
106
- const parentFeature = byId.get(parentId);
107
- if (parentFeature) {
108
- parentFeature.subfeatures.push(feature);
109
- }
110
- else {
111
- appendOrphan(orphans, parentId, feature);
112
- }
113
+ const feature = (0, util_ts_1.parseFeature)(record.line);
114
+ if (linkFeature(feature, byId, orphans)) {
115
+ items.push({ feature, record });
113
116
  }
114
117
  }
115
118
  return items;
package/dist/api.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":";;AAoBA,kCAKC;AAoCD,0CAEC;AA2BD,oCAiDC;AA3ID,uCAAwC;AAmBxC,qFAAqF;AACrF,SAAgB,WAAW,CAAC,IAAY;IACtC,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;IAC7B,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,CAAA;IACrC,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,CAAA;IACrC,OAAO,IAAI,CAAC,KAAK,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,CAAA;AAC/B,CAAC;AAED,kFAAkF;AAClF,SAAS,YAAY,CAAI,OAAyB,EAAE,GAAW,EAAE,KAAQ;IACvE,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IAC5B,IAAI,GAAG,EAAE,CAAC;QACR,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IACjB,CAAC;SAAM,CAAC;QACN,OAAO,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,KAAK,CAAC,CAAC,CAAA;IAC3B,CAAC;AACH,CAAC;AAED;;;;GAIG;AACH,SAAS,WAAW,CAAC,KAAc;IACjC,MAAM,CAAC,GAAY,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAA;IAC1D,OAAO,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAA;AAC9C,CAAC;AAED,SAAS,aAAa,CAAC,KAAc;IACnC,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACzB,OAAO,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAe,EAAE,CAAC,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAA;IAChE,CAAC;IACD,OAAO,OAAO,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;AACjD,CAAC;AAED;;;;;;GAMG;AACH,SAAgB,eAAe,CAAC,GAAW;IACzC,OAAO,YAAY,CAAC,eAAe,CAAC,GAAG,CAAC,CAAC,CAAA;AAC3C,CAAC;AAED,SAAS,eAAe,CAAC,GAAW;IAClC,MAAM,KAAK,GAAG,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,CAAA;IAChC,MAAM,OAAO,GAAiB,EAAE,CAAA;IAChC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,IAAI,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YACvD,MAAK;QACP,CAAC;QACD,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YAC9C,SAAQ;QACV,CAAC;QACD,OAAO,CAAC,IAAI,CAAC;YACX,IAAI;YACJ,UAAU,EAAE,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC;SAC/B,CAAC,CAAA;IACJ,CAAC;IACD,OAAO,OAAO,CAAA;AAChB,CAAC;AAED;;;;;;GAMG;AACH,SAAgB,YAAY,CAAC,OAAqB;IAChD,MAAM,KAAK,GAAiB,EAAE,CAAA;IAC9B,MAAM,IAAI,GAAG,IAAI,GAAG,EAAsB,CAAA;IAC1C,MAAM,OAAO,GAAG,IAAI,GAAG,EAAwB,CAAA;IAE/C,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC7B,MAAM,OAAO,GAAG,IAAA,sBAAY,EAAC,MAAM,CAAC,IAAI,EAAE,MAAM,CAAC,UAAU,CAAC,CAAA;QAE5D,IAAI,MAAM,CAAC,QAAQ,KAAK,SAAS,EAAE,CAAC;YAClC,OAAO,CAAC,SAAS,GAAG,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAA;QAC7C,CAAC;QAED,MAAM,EAAE,GAAG,WAAW,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;QAClC,MAAM,OAAO,GAAG,aAAa,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;QAE7C,mEAAmE;QACnE,oEAAoE;QACpE,qEAAqE;QACrE,oEAAoE;QACpE,IAAI,OAAO,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACzB,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;QACrB,CAAC;QAED,qEAAqE;QACrE,yEAAyE;QACzE,uEAAuE;QACvE,qEAAqE;QACrE,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,CAAC;YACxB,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,OAAO,CAAC,CAAA;YACrB,MAAM,OAAO,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;YAC/B,IAAI,OAAO,EAAE,CAAC;gBACZ,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;oBACxB,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;gBAC7B,CAAC;gBACD,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,CAAA;YACpB,CAAC;QACH,CAAC;QAED,KAAK,MAAM,QAAQ,IAAI,OAAO,EAAE,CAAC;YAC/B,MAAM,aAAa,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;YACxC,IAAI,aAAa,EAAE,CAAC;gBAClB,aAAa,CAAC,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YACzC,CAAC;iBAAM,CAAC;gBACN,YAAY,CAAC,OAAO,EAAE,QAAQ,EAAE,OAAO,CAAC,CAAA;YAC1C,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,KAAK,CAAA;AACd,CAAC"}
1
+ {"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":";;AAoBA,kCAKC;AA+ED,0CAkBC;AAWD,oCAeC;AApJD,uCAAwC;AAmBxC,qFAAqF;AACrF,SAAgB,WAAW,CAAC,IAAY;IACtC,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;IAC7B,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,CAAA;IACrC,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,CAAA;IACrC,OAAO,IAAI,CAAC,KAAK,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,CAAA;AAC/B,CAAC;AAED,kFAAkF;AAClF,SAAS,YAAY,CAAI,OAAyB,EAAE,GAAW,EAAE,KAAQ;IACvE,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IAC5B,IAAI,GAAG,EAAE,CAAC;QACR,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IACjB,CAAC;SAAM,CAAC;QACN,OAAO,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,KAAK,CAAC,CAAC,CAAA;IAC3B,CAAC;AACH,CAAC;AAED;;;;GAIG;AACH,SAAS,WAAW,CAAC,KAAc;IACjC,MAAM,CAAC,GAAY,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAA;IAC1D,OAAO,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAA;AAC9C,CAAC;AAED,SAAS,aAAa,CAAC,KAAc;IACnC,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACzB,OAAO,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAe,EAAE,CAAC,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAA;IAChE,CAAC;IACD,OAAO,OAAO,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;AACjD,CAAC;AAED;;;;GAIG;AACH,SAAS,WAAW,CAClB,OAAmB,EACnB,IAA6B,EAC7B,OAAkC;IAElC,MAAM,EAAE,GAAG,WAAW,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;IAClC,MAAM,OAAO,GAAG,aAAa,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;IAE7C,qEAAqE;IACrE,6EAA6E;IAC7E,yEAAyE;IACzE,+DAA+D;IAC/D,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,CAAC;QACxB,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,OAAO,CAAC,CAAA;QACrB,MAAM,OAAO,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;QAC/B,IAAI,OAAO,EAAE,CAAC;YACZ,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;gBACxB,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;YAC7B,CAAC;YACD,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,CAAA;QACpB,CAAC;IACH,CAAC;IAED,KAAK,MAAM,QAAQ,IAAI,OAAO,EAAE,CAAC;QAC/B,MAAM,aAAa,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;QACxC,IAAI,aAAa,EAAE,CAAC;YAClB,aAAa,CAAC,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;QACzC,CAAC;aAAM,CAAC;YACN,YAAY,CAAC,OAAO,EAAE,QAAQ,EAAE,OAAO,CAAC,CAAA;QAC1C,CAAC;IACH,CAAC;IAED,4EAA4E;IAC5E,6EAA6E;IAC7E,sEAAsE;IACtE,OAAO,OAAO,CAAC,MAAM,KAAK,CAAC,CAAA;AAC7B,CAAC;AAED;;;;;;GAMG;AACH,SAAgB,eAAe,CAAC,GAAW;IACzC,MAAM,KAAK,GAAiB,EAAE,CAAA;IAC9B,MAAM,IAAI,GAAG,IAAI,GAAG,EAAsB,CAAA;IAC1C,MAAM,OAAO,GAAG,IAAI,GAAG,EAAwB,CAAA;IAE/C,KAAK,MAAM,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,EAAE,CAAC;QACtC,IAAI,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YACvD,MAAK;QACP,CAAC;QACD,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YAC/C,MAAM,OAAO,GAAG,IAAA,sBAAY,EAAC,IAAI,CAAC,CAAA;YAClC,IAAI,WAAW,CAAC,OAAO,EAAE,IAAI,EAAE,OAAO,CAAC,EAAE,CAAC;gBACxC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YACrB,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,KAAK,CAAA;AACd,CAAC;AAED;;;;;;;;GAQG;AACH,SAAgB,YAAY,CAC1B,OAAqB;IAErB,MAAM,KAAK,GAAsB,EAAE,CAAA;IACnC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAsB,CAAA;IAC1C,MAAM,OAAO,GAAG,IAAI,GAAG,EAAwB,CAAA;IAE/C,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC7B,MAAM,OAAO,GAAG,IAAA,sBAAY,EAAC,MAAM,CAAC,IAAI,CAAC,CAAA;QACzC,IAAI,WAAW,CAAC,OAAO,EAAE,IAAI,EAAE,OAAO,CAAC,EAAE,CAAC;YACxC,KAAK,CAAC,IAAI,CAAC,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAA;QACjC,CAAC;IACH,CAAC;IAED,OAAO,KAAK,CAAA;AACd,CAAC"}
package/dist/index.d.ts CHANGED
@@ -1,2 +1,2 @@
1
1
  export { extractType, parseRecords, parseStringSync } from './api.ts';
2
- export type { GffFeature, LineRecord } from './api.ts';
2
+ export type { GffFeature, LineRecord, ParsedRecord } from './api.ts';
package/dist/util.d.ts CHANGED
@@ -29,11 +29,10 @@ export interface GffFeature {
29
29
  */
30
30
  export declare function parseAttributes(attrString: string, result: Record<string, unknown>, shouldUnescape: boolean): void;
31
31
  /**
32
- * Parse a GFF3 feature line. Pass shouldUnescape=false as a fast path for data
33
- * known to contain no escaped characters.
32
+ * Parse a GFF3 feature line. Unescaping is skipped entirely for lines with no
33
+ * '%' character, which is the common case.
34
34
  *
35
35
  * @param line - GFF3 feature line
36
- * @param shouldUnescape - whether to unescape percent-encoded values
37
36
  * @returns The parsed feature
38
37
  */
39
- export declare function parseFeature(line: string, shouldUnescape: boolean): GffFeature;
38
+ export declare function parseFeature(line: string): GffFeature;
package/dist/util.js CHANGED
@@ -137,15 +137,15 @@ function parseAttributes(attrString, result, shouldUnescape) {
137
137
  }
138
138
  }
139
139
  /**
140
- * Parse a GFF3 feature line. Pass shouldUnescape=false as a fast path for data
141
- * known to contain no escaped characters.
140
+ * Parse a GFF3 feature line. Unescaping is skipped entirely for lines with no
141
+ * '%' character, which is the common case.
142
142
  *
143
143
  * @param line - GFF3 feature line
144
- * @param shouldUnescape - whether to unescape percent-encoded values
145
144
  * @returns The parsed feature
146
145
  */
147
- function parseFeature(line, shouldUnescape) {
146
+ function parseFeature(line) {
148
147
  const f = line.split('\t');
148
+ const shouldUnescape = line.includes('%');
149
149
  const startStr = f[3];
150
150
  const endStr = f[4];
151
151
  const scoreStr = f[5];
package/dist/util.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"util.js","sourceRoot":"","sources":["../src/util.ts"],"names":[],"mappings":";AAAA,8CAA8C;AAC9C,qEAAqE;;AAerE,4BA2BC;AA8ED,0CAqDC;AAUD,oCAsBC;AA3MD,MAAM,UAAU,GAAuC,EAAE,CAAA;AACzD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC;IAC7B,MAAM,GAAG,GAAG,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;IACzD,UAAU,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;IACxC,UAAU,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;AACxD,CAAC;AAED;;;;;GAKG;AACH,SAAgB,QAAQ,CAAC,SAAiB;IACxC,MAAM,GAAG,GAAG,SAAS,CAAC,OAAO,CAAC,GAAG,CAAC,CAAA;IAClC,IAAI,GAAG,KAAK,CAAC,CAAC,EAAE,CAAC;QACf,OAAO,SAAS,CAAA;IAClB,CAAC;IAED,IAAI,MAAM,GAAG,EAAE,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,CAAC,GAAG,GAAG,CAAA;IAEX,OAAO,CAAC,GAAG,SAAS,CAAC,MAAM,EAAE,CAAC;QAC5B,MAAM,IAAI,GACR,SAAS,CAAC,CAAC,CAAC,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,SAAS,CAAC,MAAM;YAC9C,CAAC,CAAC,UAAU,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC;YAC3C,CAAC,CAAC,SAAS,CAAA;QACf,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACvB,MAAM,IAAI,SAAS,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC,GAAG,IAAI,CAAA;YAC5C,CAAC,IAAI,CAAC,CAAA;YACN,OAAO,GAAG,CAAC,CAAA;QACb,CAAC;aAAM,CAAC;YACN,mEAAmE;YACnE,wEAAwE;YACxE,CAAC,EAAE,CAAA;QACL,CAAC;IACH,CAAC;IAED,OAAO,MAAM,GAAG,SAAS,CAAC,KAAK,CAAC,OAAO,CAAC,CAAA;AAC1C,CAAC;AAED,SAAS,OAAO,CAAC,CAAS;IACxB,OAAO,CAAC,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,KAAK,GAAG,CAAA;AACpC,CAAC;AAED,SAAS,QAAQ,CACf,CAAS,EACT,cAAuB,EACvB,KAAQ;IAER,OAAO,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;AAC9D,CAAC;AAED,MAAM,sBAAsB,GAAG,IAAI,GAAG,CAAC;IACrC,OAAO;IACP,KAAK;IACL,QAAQ;IACR,OAAO;IACP,MAAM;IACN,QAAQ;IACR,OAAO;IACP,QAAQ;CACT,CAAC,CAAA;AAEF,uEAAuE;AACvE,sCAAsC;AACtC,MAAM,YAAY,GAAuC;IACvD,EAAE,EAAE,IAAI;IACR,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,aAAa,EAAE,eAAe;IAC9B,WAAW,EAAE,aAAa;IAC1B,KAAK,EAAE,OAAO;IACd,MAAM,EAAE,QAAQ;IAChB,GAAG,EAAE,KAAK;IACV,YAAY,EAAE,cAAc;IAC5B,EAAE,EAAE,IAAI;IACR,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,KAAK,EAAE,OAAO;IACd,MAAM,EAAE,QAAQ;IAChB,GAAG,EAAE,KAAK;CACX,CAAA;AAED,MAAM,UAAU,GAAuC;IACrD,GAAG,EAAE,CAAC;IACN,GAAG,EAAE,CAAC,CAAC;IACP,GAAG,EAAE,CAAC;CACP,CAAA;AAoBD;;;;GAIG;AACH,SAAgB,eAAe,CAC7B,UAAkB,EAClB,MAA+B,EAC/B,cAAuB;IAEvB,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,IAAI,UAAU,KAAK,GAAG,EAAE,CAAC;QAClD,OAAM;IACR,CAAC;IAED,IAAI,GAAG,GAAG,UAAU,CAAC,MAAM,CAAA;IAC3B,IAAI,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACjC,GAAG,GAAG,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAA;QACtD,UAAU,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;IACvC,CAAC;IAED,IAAI,KAAK,GAAG,CAAC,CAAA;IACb,OAAO,KAAK,GAAG,GAAG,EAAE,CAAC;QACnB,IAAI,OAAO,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;QAC5C,IAAI,OAAO,KAAK,CAAC,CAAC,EAAE,CAAC;YACnB,OAAO,GAAG,GAAG,CAAA;QACf,CAAC;QAED,IAAI,OAAO,GAAG,KAAK,EAAE,CAAC;YACpB,MAAM,KAAK,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;YAC5C,IAAI,KAAK,KAAK,CAAC,CAAC,IAAI,KAAK,GAAG,OAAO,IAAI,KAAK,GAAG,CAAC,GAAG,OAAO,EAAE,CAAC;gBAC3D,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,CAAA;gBAC1C,IAAI,GAAG,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;gBAC3B,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;oBACtB,GAAG,GAAG,GAAG,CAAC,WAAW,EAAE,CAAA;oBACvB,IAAI,sBAAsB,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;wBACpC,GAAG,IAAI,GAAG,CAAA;oBACZ,CAAC;gBACH,CAAC;gBAED,MAAM,MAAM,GAAa,EAAE,CAAA;gBAC3B,IAAI,QAAQ,GAAG,KAAK,GAAG,CAAC,CAAA;gBACxB,OAAO,QAAQ,GAAG,OAAO,EAAE,CAAC;oBAC1B,IAAI,QAAQ,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,QAAQ,CAAC,CAAA;oBAChD,IAAI,QAAQ,KAAK,CAAC,CAAC,IAAI,QAAQ,GAAG,OAAO,EAAE,CAAC;wBAC1C,QAAQ,GAAG,OAAO,CAAA;oBACpB,CAAC;oBACD,IAAI,QAAQ,GAAG,QAAQ,EAAE,CAAC;wBACxB,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAA;wBAChD,MAAM,CAAC,IAAI,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAA;oBACnD,CAAC;oBACD,QAAQ,GAAG,QAAQ,GAAG,CAAC,CAAA;gBACzB,CAAC;gBAED,MAAM,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;YACxD,CAAC;QACH,CAAC;QACD,KAAK,GAAG,OAAO,GAAG,CAAC,CAAA;IACrB,CAAC;AACH,CAAC;AAED;;;;;;;GAOG;AACH,SAAgB,YAAY,CAAC,IAAY,EAAE,cAAuB;IAChE,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAA;IAC1B,MAAM,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACtB,MAAM,MAAM,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACpB,MAAM,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACtB,MAAM,KAAK,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACnB,MAAM,UAAU,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IAExB,MAAM,MAAM,GAAe;QACzB,OAAO,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,EAAE,CAAC;QAC5C,MAAM,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,IAAI,CAAC;QAC7C,IAAI,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,IAAI,CAAC;QAC3C,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC;QAC5C,GAAG,EAAE,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM;QAClC,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,QAAQ;QAChD,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC,CAAC,CAAE,CAAC;QACzB,KAAK,EAAE,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,KAAK;QAC1C,WAAW,EAAE,EAAE;KAChB,CAAA;IAED,eAAe,CAAC,UAAU,EAAE,MAAM,EAAE,cAAc,CAAC,CAAA;IACnD,OAAO,MAAM,CAAA;AACf,CAAC"}
1
+ {"version":3,"file":"util.js","sourceRoot":"","sources":["../src/util.ts"],"names":[],"mappings":";AAAA,8CAA8C;AAC9C,qEAAqE;;AAerE,4BA2BC;AA8ED,0CAqDC;AASD,oCAuBC;AA3MD,MAAM,UAAU,GAAuC,EAAE,CAAA;AACzD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC;IAC7B,MAAM,GAAG,GAAG,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;IACzD,UAAU,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;IACxC,UAAU,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;AACxD,CAAC;AAED;;;;;GAKG;AACH,SAAgB,QAAQ,CAAC,SAAiB;IACxC,MAAM,GAAG,GAAG,SAAS,CAAC,OAAO,CAAC,GAAG,CAAC,CAAA;IAClC,IAAI,GAAG,KAAK,CAAC,CAAC,EAAE,CAAC;QACf,OAAO,SAAS,CAAA;IAClB,CAAC;IAED,IAAI,MAAM,GAAG,EAAE,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,CAAC,GAAG,GAAG,CAAA;IAEX,OAAO,CAAC,GAAG,SAAS,CAAC,MAAM,EAAE,CAAC;QAC5B,MAAM,IAAI,GACR,SAAS,CAAC,CAAC,CAAC,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,SAAS,CAAC,MAAM;YAC9C,CAAC,CAAC,UAAU,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC;YAC3C,CAAC,CAAC,SAAS,CAAA;QACf,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACvB,MAAM,IAAI,SAAS,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC,GAAG,IAAI,CAAA;YAC5C,CAAC,IAAI,CAAC,CAAA;YACN,OAAO,GAAG,CAAC,CAAA;QACb,CAAC;aAAM,CAAC;YACN,mEAAmE;YACnE,wEAAwE;YACxE,CAAC,EAAE,CAAA;QACL,CAAC;IACH,CAAC;IAED,OAAO,MAAM,GAAG,SAAS,CAAC,KAAK,CAAC,OAAO,CAAC,CAAA;AAC1C,CAAC;AAED,SAAS,OAAO,CAAC,CAAS;IACxB,OAAO,CAAC,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,KAAK,GAAG,CAAA;AACpC,CAAC;AAED,SAAS,QAAQ,CACf,CAAS,EACT,cAAuB,EACvB,KAAQ;IAER,OAAO,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;AAC9D,CAAC;AAED,MAAM,sBAAsB,GAAG,IAAI,GAAG,CAAC;IACrC,OAAO;IACP,KAAK;IACL,QAAQ;IACR,OAAO;IACP,MAAM;IACN,QAAQ;IACR,OAAO;IACP,QAAQ;CACT,CAAC,CAAA;AAEF,uEAAuE;AACvE,sCAAsC;AACtC,MAAM,YAAY,GAAuC;IACvD,EAAE,EAAE,IAAI;IACR,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,aAAa,EAAE,eAAe;IAC9B,WAAW,EAAE,aAAa;IAC1B,KAAK,EAAE,OAAO;IACd,MAAM,EAAE,QAAQ;IAChB,GAAG,EAAE,KAAK;IACV,YAAY,EAAE,cAAc;IAC5B,EAAE,EAAE,IAAI;IACR,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,KAAK,EAAE,OAAO;IACd,MAAM,EAAE,QAAQ;IAChB,GAAG,EAAE,KAAK;CACX,CAAA;AAED,MAAM,UAAU,GAAuC;IACrD,GAAG,EAAE,CAAC;IACN,GAAG,EAAE,CAAC,CAAC;IACP,GAAG,EAAE,CAAC;CACP,CAAA;AAoBD;;;;GAIG;AACH,SAAgB,eAAe,CAC7B,UAAkB,EAClB,MAA+B,EAC/B,cAAuB;IAEvB,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,IAAI,UAAU,KAAK,GAAG,EAAE,CAAC;QAClD,OAAM;IACR,CAAC;IAED,IAAI,GAAG,GAAG,UAAU,CAAC,MAAM,CAAA;IAC3B,IAAI,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACjC,GAAG,GAAG,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAA;QACtD,UAAU,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;IACvC,CAAC;IAED,IAAI,KAAK,GAAG,CAAC,CAAA;IACb,OAAO,KAAK,GAAG,GAAG,EAAE,CAAC;QACnB,IAAI,OAAO,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;QAC5C,IAAI,OAAO,KAAK,CAAC,CAAC,EAAE,CAAC;YACnB,OAAO,GAAG,GAAG,CAAA;QACf,CAAC;QAED,IAAI,OAAO,GAAG,KAAK,EAAE,CAAC;YACpB,MAAM,KAAK,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;YAC5C,IAAI,KAAK,KAAK,CAAC,CAAC,IAAI,KAAK,GAAG,OAAO,IAAI,KAAK,GAAG,CAAC,GAAG,OAAO,EAAE,CAAC;gBAC3D,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,CAAA;gBAC1C,IAAI,GAAG,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;gBAC3B,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;oBACtB,GAAG,GAAG,GAAG,CAAC,WAAW,EAAE,CAAA;oBACvB,IAAI,sBAAsB,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;wBACpC,GAAG,IAAI,GAAG,CAAA;oBACZ,CAAC;gBACH,CAAC;gBAED,MAAM,MAAM,GAAa,EAAE,CAAA;gBAC3B,IAAI,QAAQ,GAAG,KAAK,GAAG,CAAC,CAAA;gBACxB,OAAO,QAAQ,GAAG,OAAO,EAAE,CAAC;oBAC1B,IAAI,QAAQ,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,QAAQ,CAAC,CAAA;oBAChD,IAAI,QAAQ,KAAK,CAAC,CAAC,IAAI,QAAQ,GAAG,OAAO,EAAE,CAAC;wBAC1C,QAAQ,GAAG,OAAO,CAAA;oBACpB,CAAC;oBACD,IAAI,QAAQ,GAAG,QAAQ,EAAE,CAAC;wBACxB,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAA;wBAChD,MAAM,CAAC,IAAI,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAA;oBACnD,CAAC;oBACD,QAAQ,GAAG,QAAQ,GAAG,CAAC,CAAA;gBACzB,CAAC;gBAED,MAAM,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;YACxD,CAAC;QACH,CAAC;QACD,KAAK,GAAG,OAAO,GAAG,CAAC,CAAA;IACrB,CAAC;AACH,CAAC;AAED;;;;;;GAMG;AACH,SAAgB,YAAY,CAAC,IAAY;IACvC,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAA;IAC1B,MAAM,cAAc,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAA;IACzC,MAAM,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACtB,MAAM,MAAM,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACpB,MAAM,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACtB,MAAM,KAAK,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACnB,MAAM,UAAU,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IAExB,MAAM,MAAM,GAAe;QACzB,OAAO,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,EAAE,CAAC;QAC5C,MAAM,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,IAAI,CAAC;QAC7C,IAAI,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,IAAI,CAAC;QAC3C,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC;QAC5C,GAAG,EAAE,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM;QAClC,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,QAAQ;QAChD,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC,CAAC,CAAE,CAAC;QACzB,KAAK,EAAE,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,KAAK;QAC1C,WAAW,EAAE,EAAE;KAChB,CAAA;IAED,eAAe,CAAC,UAAU,EAAE,MAAM,EAAE,cAAc,CAAC,CAAA;IACnD,OAAO,MAAM,CAAA;AACf,CAAC"}
package/esm/api.d.ts CHANGED
@@ -1,16 +1,16 @@
1
1
  import type { GffFeature } from './util.ts';
2
- interface ParseInput {
2
+ export interface LineRecord {
3
+ /** Raw GFF3 feature line */
3
4
  line: string;
4
- lineHash?: string | number;
5
- hasEscapes: boolean;
6
5
  }
7
- export interface LineRecord extends ParseInput {
8
- /** Genomic start coordinate from the tabix index (1-based) */
9
- start: number;
10
- /** Genomic end coordinate from the tabix index */
11
- end: number;
12
- /** GFF3 feature type (column 3) */
13
- type: string;
6
+ /**
7
+ * A top-level parsed feature paired with the input record it came from. The
8
+ * parser stamps no identity onto the feature itself; callers that need a stable
9
+ * per-feature id (e.g. from a tabix byte offset) read it off their own `record`.
10
+ */
11
+ export interface ParsedRecord<R extends LineRecord = LineRecord> {
12
+ feature: GffFeature;
13
+ record: R;
14
14
  }
15
15
  /** Extract the GFF3 feature type (column 3) from a raw line without a full split. */
16
16
  export declare function extractType(line: string): string;
@@ -23,11 +23,13 @@ export declare function extractType(line: string): string;
23
23
  */
24
24
  export declare function parseStringSync(str: string): GffFeature[];
25
25
  /**
26
- * Parse an array of LineRecord objects containing raw GFF3 lines.
27
- * Supports parent/child relationships via subfeatures.
26
+ * Parse an array of records wrapping raw GFF3 lines, resolving parent/child
27
+ * relationships into `subfeatures`. Returns each top-level feature paired with
28
+ * the record it came from, so callers can attach their own identity (e.g. a
29
+ * byte offset) without the parser stamping anything onto the feature.
28
30
  *
29
- * @param records - Array of LineRecord objects with raw line and metadata
30
- * @returns array of parsed features
31
+ * @param records - Array of records, each carrying a raw GFF3 `line`
32
+ * @returns top-level features, each paired with its originating record
31
33
  */
32
- export declare function parseRecords(records: ParseInput[]): GffFeature[];
34
+ export declare function parseRecords<R extends LineRecord>(records: readonly R[]): ParsedRecord<R>[];
33
35
  export type { GffFeature } from './util.ts';
package/esm/api.js CHANGED
@@ -31,6 +31,42 @@ function toStringArray(value) {
31
31
  }
32
32
  return typeof value === 'string' ? [value] : [];
33
33
  }
34
+ /**
35
+ * Register a feature's ID and attach it to its parent(s), building the
36
+ * subfeature tree in `byId`/`orphans`. Returns true when the feature is
37
+ * top-level (has no Parent) and the caller should collect it.
38
+ */
39
+ function linkFeature(feature, byId, orphans) {
40
+ const id = firstString(feature.id);
41
+ const parents = toStringArray(feature.parent);
42
+ // Register the id only the first time it is seen. Continuation lines
43
+ // (multi-location features such as a CDS spanning several segments share one
44
+ // ID across lines) skip registration but must still be attached to their
45
+ // parent below, so this is independent of the parent handling.
46
+ if (id && !byId.has(id)) {
47
+ byId.set(id, feature);
48
+ const waiting = orphans.get(id);
49
+ if (waiting) {
50
+ for (const w of waiting) {
51
+ feature.subfeatures.push(w);
52
+ }
53
+ orphans.delete(id);
54
+ }
55
+ }
56
+ for (const parentId of parents) {
57
+ const parentFeature = byId.get(parentId);
58
+ if (parentFeature) {
59
+ parentFeature.subfeatures.push(feature);
60
+ }
61
+ else {
62
+ appendOrphan(orphans, parentId, feature);
63
+ }
64
+ }
65
+ // Every line of a top-level discontinuous feature (e.g. cDNA_match spanning
66
+ // several segments under one shared ID, with no Parent) is its own top-level
67
+ // item, so this is independent of whether the id was just registered.
68
+ return parents.length === 0;
69
+ }
34
70
  /**
35
71
  * Synchronously parse a string containing GFF3 and return an array of the
36
72
  * parsed features. Comments, directives, and `##FASTA` sections are ignored.
@@ -39,72 +75,39 @@ function toStringArray(value) {
39
75
  * @returns array of parsed features
40
76
  */
41
77
  export function parseStringSync(str) {
42
- return parseRecords(stringToRecords(str));
43
- }
44
- function stringToRecords(str) {
45
- const lines = str.split(/\r?\n/);
46
- const records = [];
47
- for (const line of lines) {
78
+ const items = [];
79
+ const byId = new Map();
80
+ const orphans = new Map();
81
+ for (const line of str.split(/\r?\n/)) {
48
82
  if (line.startsWith('##FASTA') || line.startsWith('>')) {
49
83
  break;
50
84
  }
51
- if (line.length === 0 || line.startsWith('#')) {
52
- continue;
85
+ if (line.length !== 0 && !line.startsWith('#')) {
86
+ const feature = parseFeature(line);
87
+ if (linkFeature(feature, byId, orphans)) {
88
+ items.push(feature);
89
+ }
53
90
  }
54
- records.push({
55
- line,
56
- hasEscapes: line.includes('%'),
57
- });
58
91
  }
59
- return records;
92
+ return items;
60
93
  }
61
94
  /**
62
- * Parse an array of LineRecord objects containing raw GFF3 lines.
63
- * Supports parent/child relationships via subfeatures.
95
+ * Parse an array of records wrapping raw GFF3 lines, resolving parent/child
96
+ * relationships into `subfeatures`. Returns each top-level feature paired with
97
+ * the record it came from, so callers can attach their own identity (e.g. a
98
+ * byte offset) without the parser stamping anything onto the feature.
64
99
  *
65
- * @param records - Array of LineRecord objects with raw line and metadata
66
- * @returns array of parsed features
100
+ * @param records - Array of records, each carrying a raw GFF3 `line`
101
+ * @returns top-level features, each paired with its originating record
67
102
  */
68
103
  export function parseRecords(records) {
69
104
  const items = [];
70
105
  const byId = new Map();
71
106
  const orphans = new Map();
72
107
  for (const record of records) {
73
- const feature = parseFeature(record.line, record.hasEscapes);
74
- if (record.lineHash !== undefined) {
75
- feature._lineHash = String(record.lineHash);
76
- }
77
- const id = firstString(feature.id);
78
- const parents = toStringArray(feature.parent);
79
- // A parentless line is a top-level item. Every line of a top-level
80
- // discontinuous feature (e.g. cDNA_match/EST_match spanning several
81
- // segments under one shared ID, with no Parent) is its own top-level
82
- // item, so push regardless of whether the id is already registered.
83
- if (parents.length === 0) {
84
- items.push(feature);
85
- }
86
- // Register the id only the first time it is seen. Continuation lines
87
- // (multi-location features such as a CDS spanning several segments share
88
- // one ID across lines) skip registration but must still be attached to
89
- // their parent below, so this is independent of the parent handling.
90
- if (id && !byId.has(id)) {
91
- byId.set(id, feature);
92
- const waiting = orphans.get(id);
93
- if (waiting) {
94
- for (const w of waiting) {
95
- feature.subfeatures.push(w);
96
- }
97
- orphans.delete(id);
98
- }
99
- }
100
- for (const parentId of parents) {
101
- const parentFeature = byId.get(parentId);
102
- if (parentFeature) {
103
- parentFeature.subfeatures.push(feature);
104
- }
105
- else {
106
- appendOrphan(orphans, parentId, feature);
107
- }
108
+ const feature = parseFeature(record.line);
109
+ if (linkFeature(feature, byId, orphans)) {
110
+ items.push({ feature, record });
108
111
  }
109
112
  }
110
113
  return items;
package/esm/api.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,WAAW,CAAA;AAmBxC,qFAAqF;AACrF,MAAM,UAAU,WAAW,CAAC,IAAY;IACtC,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;IAC7B,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,CAAA;IACrC,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,CAAA;IACrC,OAAO,IAAI,CAAC,KAAK,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,CAAA;AAC/B,CAAC;AAED,kFAAkF;AAClF,SAAS,YAAY,CAAI,OAAyB,EAAE,GAAW,EAAE,KAAQ;IACvE,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IAC5B,IAAI,GAAG,EAAE,CAAC;QACR,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IACjB,CAAC;SAAM,CAAC;QACN,OAAO,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,KAAK,CAAC,CAAC,CAAA;IAC3B,CAAC;AACH,CAAC;AAED;;;;GAIG;AACH,SAAS,WAAW,CAAC,KAAc;IACjC,MAAM,CAAC,GAAY,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAA;IAC1D,OAAO,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAA;AAC9C,CAAC;AAED,SAAS,aAAa,CAAC,KAAc;IACnC,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACzB,OAAO,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAe,EAAE,CAAC,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAA;IAChE,CAAC;IACD,OAAO,OAAO,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;AACjD,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,eAAe,CAAC,GAAW;IACzC,OAAO,YAAY,CAAC,eAAe,CAAC,GAAG,CAAC,CAAC,CAAA;AAC3C,CAAC;AAED,SAAS,eAAe,CAAC,GAAW;IAClC,MAAM,KAAK,GAAG,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,CAAA;IAChC,MAAM,OAAO,GAAiB,EAAE,CAAA;IAChC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,IAAI,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YACvD,MAAK;QACP,CAAC;QACD,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YAC9C,SAAQ;QACV,CAAC;QACD,OAAO,CAAC,IAAI,CAAC;YACX,IAAI;YACJ,UAAU,EAAE,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC;SAC/B,CAAC,CAAA;IACJ,CAAC;IACD,OAAO,OAAO,CAAA;AAChB,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,YAAY,CAAC,OAAqB;IAChD,MAAM,KAAK,GAAiB,EAAE,CAAA;IAC9B,MAAM,IAAI,GAAG,IAAI,GAAG,EAAsB,CAAA;IAC1C,MAAM,OAAO,GAAG,IAAI,GAAG,EAAwB,CAAA;IAE/C,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC7B,MAAM,OAAO,GAAG,YAAY,CAAC,MAAM,CAAC,IAAI,EAAE,MAAM,CAAC,UAAU,CAAC,CAAA;QAE5D,IAAI,MAAM,CAAC,QAAQ,KAAK,SAAS,EAAE,CAAC;YAClC,OAAO,CAAC,SAAS,GAAG,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAA;QAC7C,CAAC;QAED,MAAM,EAAE,GAAG,WAAW,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;QAClC,MAAM,OAAO,GAAG,aAAa,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;QAE7C,mEAAmE;QACnE,oEAAoE;QACpE,qEAAqE;QACrE,oEAAoE;QACpE,IAAI,OAAO,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACzB,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;QACrB,CAAC;QAED,qEAAqE;QACrE,yEAAyE;QACzE,uEAAuE;QACvE,qEAAqE;QACrE,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,CAAC;YACxB,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,OAAO,CAAC,CAAA;YACrB,MAAM,OAAO,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;YAC/B,IAAI,OAAO,EAAE,CAAC;gBACZ,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;oBACxB,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;gBAC7B,CAAC;gBACD,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,CAAA;YACpB,CAAC;QACH,CAAC;QAED,KAAK,MAAM,QAAQ,IAAI,OAAO,EAAE,CAAC;YAC/B,MAAM,aAAa,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;YACxC,IAAI,aAAa,EAAE,CAAC;gBAClB,aAAa,CAAC,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YACzC,CAAC;iBAAM,CAAC;gBACN,YAAY,CAAC,OAAO,EAAE,QAAQ,EAAE,OAAO,CAAC,CAAA;YAC1C,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,KAAK,CAAA;AACd,CAAC"}
1
+ {"version":3,"file":"api.js","sourceRoot":"","sources":["../src/api.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,WAAW,CAAA;AAmBxC,qFAAqF;AACrF,MAAM,UAAU,WAAW,CAAC,IAAY;IACtC,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;IAC7B,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,CAAA;IACrC,MAAM,EAAE,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,GAAG,CAAC,CAAC,CAAA;IACrC,OAAO,IAAI,CAAC,KAAK,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,CAAA;AAC/B,CAAC;AAED,kFAAkF;AAClF,SAAS,YAAY,CAAI,OAAyB,EAAE,GAAW,EAAE,KAAQ;IACvE,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IAC5B,IAAI,GAAG,EAAE,CAAC;QACR,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IACjB,CAAC;SAAM,CAAC;QACN,OAAO,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,KAAK,CAAC,CAAC,CAAA;IAC3B,CAAC;AACH,CAAC;AAED;;;;GAIG;AACH,SAAS,WAAW,CAAC,KAAc;IACjC,MAAM,CAAC,GAAY,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAA;IAC1D,OAAO,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAA;AAC9C,CAAC;AAED,SAAS,aAAa,CAAC,KAAc;IACnC,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACzB,OAAO,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAe,EAAE,CAAC,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAA;IAChE,CAAC;IACD,OAAO,OAAO,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;AACjD,CAAC;AAED;;;;GAIG;AACH,SAAS,WAAW,CAClB,OAAmB,EACnB,IAA6B,EAC7B,OAAkC;IAElC,MAAM,EAAE,GAAG,WAAW,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;IAClC,MAAM,OAAO,GAAG,aAAa,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;IAE7C,qEAAqE;IACrE,6EAA6E;IAC7E,yEAAyE;IACzE,+DAA+D;IAC/D,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,CAAC;QACxB,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,OAAO,CAAC,CAAA;QACrB,MAAM,OAAO,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;QAC/B,IAAI,OAAO,EAAE,CAAC;YACZ,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;gBACxB,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;YAC7B,CAAC;YACD,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,CAAA;QACpB,CAAC;IACH,CAAC;IAED,KAAK,MAAM,QAAQ,IAAI,OAAO,EAAE,CAAC;QAC/B,MAAM,aAAa,GAAG,IAAI,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;QACxC,IAAI,aAAa,EAAE,CAAC;YAClB,aAAa,CAAC,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;QACzC,CAAC;aAAM,CAAC;YACN,YAAY,CAAC,OAAO,EAAE,QAAQ,EAAE,OAAO,CAAC,CAAA;QAC1C,CAAC;IACH,CAAC;IAED,4EAA4E;IAC5E,6EAA6E;IAC7E,sEAAsE;IACtE,OAAO,OAAO,CAAC,MAAM,KAAK,CAAC,CAAA;AAC7B,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,eAAe,CAAC,GAAW;IACzC,MAAM,KAAK,GAAiB,EAAE,CAAA;IAC9B,MAAM,IAAI,GAAG,IAAI,GAAG,EAAsB,CAAA;IAC1C,MAAM,OAAO,GAAG,IAAI,GAAG,EAAwB,CAAA;IAE/C,KAAK,MAAM,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,OAAO,CAAC,EAAE,CAAC;QACtC,IAAI,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YACvD,MAAK;QACP,CAAC;QACD,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YAC/C,MAAM,OAAO,GAAG,YAAY,CAAC,IAAI,CAAC,CAAA;YAClC,IAAI,WAAW,CAAC,OAAO,EAAE,IAAI,EAAE,OAAO,CAAC,EAAE,CAAC;gBACxC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YACrB,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,KAAK,CAAA;AACd,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,UAAU,YAAY,CAC1B,OAAqB;IAErB,MAAM,KAAK,GAAsB,EAAE,CAAA;IACnC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAsB,CAAA;IAC1C,MAAM,OAAO,GAAG,IAAI,GAAG,EAAwB,CAAA;IAE/C,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC7B,MAAM,OAAO,GAAG,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;QACzC,IAAI,WAAW,CAAC,OAAO,EAAE,IAAI,EAAE,OAAO,CAAC,EAAE,CAAC;YACxC,KAAK,CAAC,IAAI,CAAC,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAA;QACjC,CAAC;IACH,CAAC;IAED,OAAO,KAAK,CAAA;AACd,CAAC"}
package/esm/index.d.ts CHANGED
@@ -1,2 +1,2 @@
1
1
  export { extractType, parseRecords, parseStringSync } from './api.ts';
2
- export type { GffFeature, LineRecord } from './api.ts';
2
+ export type { GffFeature, LineRecord, ParsedRecord } from './api.ts';
package/esm/util.d.ts CHANGED
@@ -29,11 +29,10 @@ export interface GffFeature {
29
29
  */
30
30
  export declare function parseAttributes(attrString: string, result: Record<string, unknown>, shouldUnescape: boolean): void;
31
31
  /**
32
- * Parse a GFF3 feature line. Pass shouldUnescape=false as a fast path for data
33
- * known to contain no escaped characters.
32
+ * Parse a GFF3 feature line. Unescaping is skipped entirely for lines with no
33
+ * '%' character, which is the common case.
34
34
  *
35
35
  * @param line - GFF3 feature line
36
- * @param shouldUnescape - whether to unescape percent-encoded values
37
36
  * @returns The parsed feature
38
37
  */
39
- export declare function parseFeature(line: string, shouldUnescape: boolean): GffFeature;
38
+ export declare function parseFeature(line: string): GffFeature;
package/esm/util.js CHANGED
@@ -132,15 +132,15 @@ export function parseAttributes(attrString, result, shouldUnescape) {
132
132
  }
133
133
  }
134
134
  /**
135
- * Parse a GFF3 feature line. Pass shouldUnescape=false as a fast path for data
136
- * known to contain no escaped characters.
135
+ * Parse a GFF3 feature line. Unescaping is skipped entirely for lines with no
136
+ * '%' character, which is the common case.
137
137
  *
138
138
  * @param line - GFF3 feature line
139
- * @param shouldUnescape - whether to unescape percent-encoded values
140
139
  * @returns The parsed feature
141
140
  */
142
- export function parseFeature(line, shouldUnescape) {
141
+ export function parseFeature(line) {
143
142
  const f = line.split('\t');
143
+ const shouldUnescape = line.includes('%');
144
144
  const startStr = f[3];
145
145
  const endStr = f[4];
146
146
  const scoreStr = f[5];
package/esm/util.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"util.js","sourceRoot":"","sources":["../src/util.ts"],"names":[],"mappings":"AAAA,8CAA8C;AAC9C,qEAAqE;AAErE,MAAM,UAAU,GAAuC,EAAE,CAAA;AACzD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC;IAC7B,MAAM,GAAG,GAAG,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;IACzD,UAAU,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;IACxC,UAAU,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;AACxD,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,QAAQ,CAAC,SAAiB;IACxC,MAAM,GAAG,GAAG,SAAS,CAAC,OAAO,CAAC,GAAG,CAAC,CAAA;IAClC,IAAI,GAAG,KAAK,CAAC,CAAC,EAAE,CAAC;QACf,OAAO,SAAS,CAAA;IAClB,CAAC;IAED,IAAI,MAAM,GAAG,EAAE,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,CAAC,GAAG,GAAG,CAAA;IAEX,OAAO,CAAC,GAAG,SAAS,CAAC,MAAM,EAAE,CAAC;QAC5B,MAAM,IAAI,GACR,SAAS,CAAC,CAAC,CAAC,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,SAAS,CAAC,MAAM;YAC9C,CAAC,CAAC,UAAU,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC;YAC3C,CAAC,CAAC,SAAS,CAAA;QACf,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACvB,MAAM,IAAI,SAAS,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC,GAAG,IAAI,CAAA;YAC5C,CAAC,IAAI,CAAC,CAAA;YACN,OAAO,GAAG,CAAC,CAAA;QACb,CAAC;aAAM,CAAC;YACN,mEAAmE;YACnE,wEAAwE;YACxE,CAAC,EAAE,CAAA;QACL,CAAC;IACH,CAAC;IAED,OAAO,MAAM,GAAG,SAAS,CAAC,KAAK,CAAC,OAAO,CAAC,CAAA;AAC1C,CAAC;AAED,SAAS,OAAO,CAAC,CAAS;IACxB,OAAO,CAAC,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,KAAK,GAAG,CAAA;AACpC,CAAC;AAED,SAAS,QAAQ,CACf,CAAS,EACT,cAAuB,EACvB,KAAQ;IAER,OAAO,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;AAC9D,CAAC;AAED,MAAM,sBAAsB,GAAG,IAAI,GAAG,CAAC;IACrC,OAAO;IACP,KAAK;IACL,QAAQ;IACR,OAAO;IACP,MAAM;IACN,QAAQ;IACR,OAAO;IACP,QAAQ;CACT,CAAC,CAAA;AAEF,uEAAuE;AACvE,sCAAsC;AACtC,MAAM,YAAY,GAAuC;IACvD,EAAE,EAAE,IAAI;IACR,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,aAAa,EAAE,eAAe;IAC9B,WAAW,EAAE,aAAa;IAC1B,KAAK,EAAE,OAAO;IACd,MAAM,EAAE,QAAQ;IAChB,GAAG,EAAE,KAAK;IACV,YAAY,EAAE,cAAc;IAC5B,EAAE,EAAE,IAAI;IACR,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,KAAK,EAAE,OAAO;IACd,MAAM,EAAE,QAAQ;IAChB,GAAG,EAAE,KAAK;CACX,CAAA;AAED,MAAM,UAAU,GAAuC;IACrD,GAAG,EAAE,CAAC;IACN,GAAG,EAAE,CAAC,CAAC;IACP,GAAG,EAAE,CAAC;CACP,CAAA;AAoBD;;;;GAIG;AACH,MAAM,UAAU,eAAe,CAC7B,UAAkB,EAClB,MAA+B,EAC/B,cAAuB;IAEvB,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,IAAI,UAAU,KAAK,GAAG,EAAE,CAAC;QAClD,OAAM;IACR,CAAC;IAED,IAAI,GAAG,GAAG,UAAU,CAAC,MAAM,CAAA;IAC3B,IAAI,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACjC,GAAG,GAAG,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAA;QACtD,UAAU,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;IACvC,CAAC;IAED,IAAI,KAAK,GAAG,CAAC,CAAA;IACb,OAAO,KAAK,GAAG,GAAG,EAAE,CAAC;QACnB,IAAI,OAAO,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;QAC5C,IAAI,OAAO,KAAK,CAAC,CAAC,EAAE,CAAC;YACnB,OAAO,GAAG,GAAG,CAAA;QACf,CAAC;QAED,IAAI,OAAO,GAAG,KAAK,EAAE,CAAC;YACpB,MAAM,KAAK,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;YAC5C,IAAI,KAAK,KAAK,CAAC,CAAC,IAAI,KAAK,GAAG,OAAO,IAAI,KAAK,GAAG,CAAC,GAAG,OAAO,EAAE,CAAC;gBAC3D,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,CAAA;gBAC1C,IAAI,GAAG,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;gBAC3B,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;oBACtB,GAAG,GAAG,GAAG,CAAC,WAAW,EAAE,CAAA;oBACvB,IAAI,sBAAsB,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;wBACpC,GAAG,IAAI,GAAG,CAAA;oBACZ,CAAC;gBACH,CAAC;gBAED,MAAM,MAAM,GAAa,EAAE,CAAA;gBAC3B,IAAI,QAAQ,GAAG,KAAK,GAAG,CAAC,CAAA;gBACxB,OAAO,QAAQ,GAAG,OAAO,EAAE,CAAC;oBAC1B,IAAI,QAAQ,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,QAAQ,CAAC,CAAA;oBAChD,IAAI,QAAQ,KAAK,CAAC,CAAC,IAAI,QAAQ,GAAG,OAAO,EAAE,CAAC;wBAC1C,QAAQ,GAAG,OAAO,CAAA;oBACpB,CAAC;oBACD,IAAI,QAAQ,GAAG,QAAQ,EAAE,CAAC;wBACxB,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAA;wBAChD,MAAM,CAAC,IAAI,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAA;oBACnD,CAAC;oBACD,QAAQ,GAAG,QAAQ,GAAG,CAAC,CAAA;gBACzB,CAAC;gBAED,MAAM,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;YACxD,CAAC;QACH,CAAC;QACD,KAAK,GAAG,OAAO,GAAG,CAAC,CAAA;IACrB,CAAC;AACH,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,YAAY,CAAC,IAAY,EAAE,cAAuB;IAChE,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAA;IAC1B,MAAM,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACtB,MAAM,MAAM,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACpB,MAAM,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACtB,MAAM,KAAK,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACnB,MAAM,UAAU,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IAExB,MAAM,MAAM,GAAe;QACzB,OAAO,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,EAAE,CAAC;QAC5C,MAAM,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,IAAI,CAAC;QAC7C,IAAI,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,IAAI,CAAC;QAC3C,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC;QAC5C,GAAG,EAAE,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM;QAClC,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,QAAQ;QAChD,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC,CAAC,CAAE,CAAC;QACzB,KAAK,EAAE,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,KAAK;QAC1C,WAAW,EAAE,EAAE;KAChB,CAAA;IAED,eAAe,CAAC,UAAU,EAAE,MAAM,EAAE,cAAc,CAAC,CAAA;IACnD,OAAO,MAAM,CAAA;AACf,CAAC"}
1
+ {"version":3,"file":"util.js","sourceRoot":"","sources":["../src/util.ts"],"names":[],"mappings":"AAAA,8CAA8C;AAC9C,qEAAqE;AAErE,MAAM,UAAU,GAAuC,EAAE,CAAA;AACzD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC;IAC7B,MAAM,GAAG,GAAG,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;IACzD,UAAU,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;IACxC,UAAU,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;AACxD,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,QAAQ,CAAC,SAAiB;IACxC,MAAM,GAAG,GAAG,SAAS,CAAC,OAAO,CAAC,GAAG,CAAC,CAAA;IAClC,IAAI,GAAG,KAAK,CAAC,CAAC,EAAE,CAAC;QACf,OAAO,SAAS,CAAA;IAClB,CAAC;IAED,IAAI,MAAM,GAAG,EAAE,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,CAAC,GAAG,GAAG,CAAA;IAEX,OAAO,CAAC,GAAG,SAAS,CAAC,MAAM,EAAE,CAAC;QAC5B,MAAM,IAAI,GACR,SAAS,CAAC,CAAC,CAAC,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,SAAS,CAAC,MAAM;YAC9C,CAAC,CAAC,UAAU,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC;YAC3C,CAAC,CAAC,SAAS,CAAA;QACf,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACvB,MAAM,IAAI,SAAS,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC,GAAG,IAAI,CAAA;YAC5C,CAAC,IAAI,CAAC,CAAA;YACN,OAAO,GAAG,CAAC,CAAA;QACb,CAAC;aAAM,CAAC;YACN,mEAAmE;YACnE,wEAAwE;YACxE,CAAC,EAAE,CAAA;QACL,CAAC;IACH,CAAC;IAED,OAAO,MAAM,GAAG,SAAS,CAAC,KAAK,CAAC,OAAO,CAAC,CAAA;AAC1C,CAAC;AAED,SAAS,OAAO,CAAC,CAAS;IACxB,OAAO,CAAC,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,KAAK,GAAG,CAAA;AACpC,CAAC;AAED,SAAS,QAAQ,CACf,CAAS,EACT,cAAuB,EACvB,KAAQ;IAER,OAAO,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;AAC9D,CAAC;AAED,MAAM,sBAAsB,GAAG,IAAI,GAAG,CAAC;IACrC,OAAO;IACP,KAAK;IACL,QAAQ;IACR,OAAO;IACP,MAAM;IACN,QAAQ;IACR,OAAO;IACP,QAAQ;CACT,CAAC,CAAA;AAEF,uEAAuE;AACvE,sCAAsC;AACtC,MAAM,YAAY,GAAuC;IACvD,EAAE,EAAE,IAAI;IACR,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,aAAa,EAAE,eAAe;IAC9B,WAAW,EAAE,aAAa;IAC1B,KAAK,EAAE,OAAO;IACd,MAAM,EAAE,QAAQ;IAChB,GAAG,EAAE,KAAK;IACV,YAAY,EAAE,cAAc;IAC5B,EAAE,EAAE,IAAI;IACR,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,IAAI,EAAE,MAAM;IACZ,MAAM,EAAE,QAAQ;IAChB,KAAK,EAAE,OAAO;IACd,MAAM,EAAE,QAAQ;IAChB,GAAG,EAAE,KAAK;CACX,CAAA;AAED,MAAM,UAAU,GAAuC;IACrD,GAAG,EAAE,CAAC;IACN,GAAG,EAAE,CAAC,CAAC;IACP,GAAG,EAAE,CAAC;CACP,CAAA;AAoBD;;;;GAIG;AACH,MAAM,UAAU,eAAe,CAC7B,UAAkB,EAClB,MAA+B,EAC/B,cAAuB;IAEvB,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,IAAI,UAAU,KAAK,GAAG,EAAE,CAAC;QAClD,OAAM;IACR,CAAC;IAED,IAAI,GAAG,GAAG,UAAU,CAAC,MAAM,CAAA;IAC3B,IAAI,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACjC,GAAG,GAAG,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAA;QACtD,UAAU,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;IACvC,CAAC;IAED,IAAI,KAAK,GAAG,CAAC,CAAA;IACb,OAAO,KAAK,GAAG,GAAG,EAAE,CAAC;QACnB,IAAI,OAAO,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;QAC5C,IAAI,OAAO,KAAK,CAAC,CAAC,EAAE,CAAC;YACnB,OAAO,GAAG,GAAG,CAAA;QACf,CAAC;QAED,IAAI,OAAO,GAAG,KAAK,EAAE,CAAC;YACpB,MAAM,KAAK,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;YAC5C,IAAI,KAAK,KAAK,CAAC,CAAC,IAAI,KAAK,GAAG,OAAO,IAAI,KAAK,GAAG,CAAC,GAAG,OAAO,EAAE,CAAC;gBAC3D,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,CAAA;gBAC1C,IAAI,GAAG,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;gBAC3B,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;oBACtB,GAAG,GAAG,GAAG,CAAC,WAAW,EAAE,CAAA;oBACvB,IAAI,sBAAsB,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;wBACpC,GAAG,IAAI,GAAG,CAAA;oBACZ,CAAC;gBACH,CAAC;gBAED,MAAM,MAAM,GAAa,EAAE,CAAA;gBAC3B,IAAI,QAAQ,GAAG,KAAK,GAAG,CAAC,CAAA;gBACxB,OAAO,QAAQ,GAAG,OAAO,EAAE,CAAC;oBAC1B,IAAI,QAAQ,GAAG,UAAU,CAAC,OAAO,CAAC,GAAG,EAAE,QAAQ,CAAC,CAAA;oBAChD,IAAI,QAAQ,KAAK,CAAC,CAAC,IAAI,QAAQ,GAAG,OAAO,EAAE,CAAC;wBAC1C,QAAQ,GAAG,OAAO,CAAA;oBACpB,CAAC;oBACD,IAAI,QAAQ,GAAG,QAAQ,EAAE,CAAC;wBACxB,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAA;wBAChD,MAAM,CAAC,IAAI,CAAC,cAAc,CAAC,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAA;oBACnD,CAAC;oBACD,QAAQ,GAAG,QAAQ,GAAG,CAAC,CAAA;gBACzB,CAAC;gBAED,MAAM,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;YACxD,CAAC;QACH,CAAC;QACD,KAAK,GAAG,OAAO,GAAG,CAAC,CAAA;IACrB,CAAC;AACH,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,YAAY,CAAC,IAAY;IACvC,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAA;IAC1B,MAAM,cAAc,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAA;IACzC,MAAM,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACtB,MAAM,MAAM,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACpB,MAAM,QAAQ,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACtB,MAAM,KAAK,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IACnB,MAAM,UAAU,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IAExB,MAAM,MAAM,GAAe;QACzB,OAAO,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,EAAE,CAAC;QAC5C,MAAM,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,IAAI,CAAC;QAC7C,IAAI,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAE,EAAE,cAAc,EAAE,IAAI,CAAC;QAC3C,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC;QAC5C,GAAG,EAAE,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM;QAClC,KAAK,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,QAAQ;QAChD,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC,CAAC,CAAE,CAAC;QACzB,KAAK,EAAE,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,KAAK;QAC1C,WAAW,EAAE,EAAE;KAChB,CAAA;IAED,eAAe,CAAC,UAAU,EAAE,MAAM,EAAE,cAAc,CAAC,CAAA;IACnD,OAAO,MAAM,CAAA;AACf,CAAC"}
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gff-nostream",
3
- "version": "4.0.0",
3
+ "version": "5.0.0",
4
4
  "description": "utilities to read GFF3 data",
5
5
  "license": "MIT",
6
6
  "repository": {
package/src/api.ts CHANGED
@@ -2,19 +2,19 @@ import { parseFeature } from './util.ts'
2
2
 
3
3
  import type { GffFeature } from './util.ts'
4
4
 
5
- interface ParseInput {
5
+ export interface LineRecord {
6
+ /** Raw GFF3 feature line */
6
7
  line: string
7
- lineHash?: string | number
8
- hasEscapes: boolean
9
8
  }
10
9
 
11
- export interface LineRecord extends ParseInput {
12
- /** Genomic start coordinate from the tabix index (1-based) */
13
- start: number
14
- /** Genomic end coordinate from the tabix index */
15
- end: number
16
- /** GFF3 feature type (column 3) */
17
- type: string
10
+ /**
11
+ * A top-level parsed feature paired with the input record it came from. The
12
+ * parser stamps no identity onto the feature itself; callers that need a stable
13
+ * per-feature id (e.g. from a tabix byte offset) read it off their own `record`.
14
+ */
15
+ export interface ParsedRecord<R extends LineRecord = LineRecord> {
16
+ feature: GffFeature
17
+ record: R
18
18
  }
19
19
 
20
20
  /** Extract the GFF3 feature type (column 3) from a raw line without a full split. */
@@ -52,6 +52,49 @@ function toStringArray(value: unknown): string[] {
52
52
  return typeof value === 'string' ? [value] : []
53
53
  }
54
54
 
55
+ /**
56
+ * Register a feature's ID and attach it to its parent(s), building the
57
+ * subfeature tree in `byId`/`orphans`. Returns true when the feature is
58
+ * top-level (has no Parent) and the caller should collect it.
59
+ */
60
+ function linkFeature(
61
+ feature: GffFeature,
62
+ byId: Map<string, GffFeature>,
63
+ orphans: Map<string, GffFeature[]>,
64
+ ): boolean {
65
+ const id = firstString(feature.id)
66
+ const parents = toStringArray(feature.parent)
67
+
68
+ // Register the id only the first time it is seen. Continuation lines
69
+ // (multi-location features such as a CDS spanning several segments share one
70
+ // ID across lines) skip registration but must still be attached to their
71
+ // parent below, so this is independent of the parent handling.
72
+ if (id && !byId.has(id)) {
73
+ byId.set(id, feature)
74
+ const waiting = orphans.get(id)
75
+ if (waiting) {
76
+ for (const w of waiting) {
77
+ feature.subfeatures.push(w)
78
+ }
79
+ orphans.delete(id)
80
+ }
81
+ }
82
+
83
+ for (const parentId of parents) {
84
+ const parentFeature = byId.get(parentId)
85
+ if (parentFeature) {
86
+ parentFeature.subfeatures.push(feature)
87
+ } else {
88
+ appendOrphan(orphans, parentId, feature)
89
+ }
90
+ }
91
+
92
+ // Every line of a top-level discontinuous feature (e.g. cDNA_match spanning
93
+ // several segments under one shared ID, with no Parent) is its own top-level
94
+ // item, so this is independent of whether the id was just registered.
95
+ return parents.length === 0
96
+ }
97
+
55
98
  /**
56
99
  * Synchronously parse a string containing GFF3 and return an array of the
57
100
  * parsed features. Comments, directives, and `##FASTA` sections are ignored.
@@ -60,79 +103,45 @@ function toStringArray(value: unknown): string[] {
60
103
  * @returns array of parsed features
61
104
  */
62
105
  export function parseStringSync(str: string): GffFeature[] {
63
- return parseRecords(stringToRecords(str))
64
- }
106
+ const items: GffFeature[] = []
107
+ const byId = new Map<string, GffFeature>()
108
+ const orphans = new Map<string, GffFeature[]>()
65
109
 
66
- function stringToRecords(str: string) {
67
- const lines = str.split(/\r?\n/)
68
- const records: ParseInput[] = []
69
- for (const line of lines) {
110
+ for (const line of str.split(/\r?\n/)) {
70
111
  if (line.startsWith('##FASTA') || line.startsWith('>')) {
71
112
  break
72
113
  }
73
- if (line.length === 0 || line.startsWith('#')) {
74
- continue
114
+ if (line.length !== 0 && !line.startsWith('#')) {
115
+ const feature = parseFeature(line)
116
+ if (linkFeature(feature, byId, orphans)) {
117
+ items.push(feature)
118
+ }
75
119
  }
76
- records.push({
77
- line,
78
- hasEscapes: line.includes('%'),
79
- })
80
120
  }
81
- return records
121
+
122
+ return items
82
123
  }
83
124
 
84
125
  /**
85
- * Parse an array of LineRecord objects containing raw GFF3 lines.
86
- * Supports parent/child relationships via subfeatures.
126
+ * Parse an array of records wrapping raw GFF3 lines, resolving parent/child
127
+ * relationships into `subfeatures`. Returns each top-level feature paired with
128
+ * the record it came from, so callers can attach their own identity (e.g. a
129
+ * byte offset) without the parser stamping anything onto the feature.
87
130
  *
88
- * @param records - Array of LineRecord objects with raw line and metadata
89
- * @returns array of parsed features
131
+ * @param records - Array of records, each carrying a raw GFF3 `line`
132
+ * @returns top-level features, each paired with its originating record
90
133
  */
91
- export function parseRecords(records: ParseInput[]): GffFeature[] {
92
- const items: GffFeature[] = []
134
+ export function parseRecords<R extends LineRecord>(
135
+ records: readonly R[],
136
+ ): ParsedRecord<R>[] {
137
+ const items: ParsedRecord<R>[] = []
93
138
  const byId = new Map<string, GffFeature>()
94
139
  const orphans = new Map<string, GffFeature[]>()
95
140
 
96
141
  for (const record of records) {
97
- const feature = parseFeature(record.line, record.hasEscapes)
98
-
99
- if (record.lineHash !== undefined) {
100
- feature._lineHash = String(record.lineHash)
101
- }
102
-
103
- const id = firstString(feature.id)
104
- const parents = toStringArray(feature.parent)
105
-
106
- // A parentless line is a top-level item. Every line of a top-level
107
- // discontinuous feature (e.g. cDNA_match/EST_match spanning several
108
- // segments under one shared ID, with no Parent) is its own top-level
109
- // item, so push regardless of whether the id is already registered.
110
- if (parents.length === 0) {
111
- items.push(feature)
112
- }
113
-
114
- // Register the id only the first time it is seen. Continuation lines
115
- // (multi-location features such as a CDS spanning several segments share
116
- // one ID across lines) skip registration but must still be attached to
117
- // their parent below, so this is independent of the parent handling.
118
- if (id && !byId.has(id)) {
119
- byId.set(id, feature)
120
- const waiting = orphans.get(id)
121
- if (waiting) {
122
- for (const w of waiting) {
123
- feature.subfeatures.push(w)
124
- }
125
- orphans.delete(id)
126
- }
127
- }
128
-
129
- for (const parentId of parents) {
130
- const parentFeature = byId.get(parentId)
131
- if (parentFeature) {
132
- parentFeature.subfeatures.push(feature)
133
- } else {
134
- appendOrphan(orphans, parentId, feature)
135
- }
142
+ const feature = parseFeature(record.line)
143
+ if (linkFeature(feature, byId, orphans)) {
144
+ items.push({ feature, record })
136
145
  }
137
146
  }
138
147
 
package/src/index.ts CHANGED
@@ -1,3 +1,3 @@
1
1
  export { extractType, parseRecords, parseStringSync } from './api.ts'
2
2
 
3
- export type { GffFeature, LineRecord } from './api.ts'
3
+ export type { GffFeature, LineRecord, ParsedRecord } from './api.ts'
package/src/util.ts CHANGED
@@ -175,15 +175,15 @@ export function parseAttributes(
175
175
  }
176
176
 
177
177
  /**
178
- * Parse a GFF3 feature line. Pass shouldUnescape=false as a fast path for data
179
- * known to contain no escaped characters.
178
+ * Parse a GFF3 feature line. Unescaping is skipped entirely for lines with no
179
+ * '%' character, which is the common case.
180
180
  *
181
181
  * @param line - GFF3 feature line
182
- * @param shouldUnescape - whether to unescape percent-encoded values
183
182
  * @returns The parsed feature
184
183
  */
185
- export function parseFeature(line: string, shouldUnescape: boolean): GffFeature {
184
+ export function parseFeature(line: string): GffFeature {
186
185
  const f = line.split('\t')
186
+ const shouldUnescape = line.includes('%')
187
187
  const startStr = f[3]!
188
188
  const endStr = f[4]!
189
189
  const scoreStr = f[5]!