@limaformat/lima 0.5.0 → 0.5.1

package/CHANGELOG.md

@@ -12,6 +12,27 @@ are both frozen regardless of what this file shows.
 
 ## [Unreleased]
 
+## [0.5.1] — 2026-10-28
+
+Core errata `1.0.10`: aligned top-level values are trimmed, as Core 1.0
+always required.
+
+### Fixed
+
+- A top-level inline value kept every space after `: ` but the first:
+  `title:   Hello` read `'  Hello'`, and `n:    42` the string `'   42'`
+  instead of the integer 42 — against §4 step 3 and the §4 and §5.1
+  examples. Nested keys were not affected. The top-level entry now skips the
+  whitespace after the separator before reading the value, as the block
+  mapping does; the References 2.0 columns it reports were already physical
+  and are unchanged.
+
+The shared conformance corpus grows to 218 Core cases (7 new, `since:
+"1.0.10"`); TypeScript, Rust, and Go pass all of them.
+
+A unit test in `src/block.test.ts` had asserted the defect (`key:  value`
+→ `' value'`); it now asserts the specified `'value'`.
+
 ## [0.5.0] — 2026-09-09
 
 Scope cleanup. The frozen **References 1.0** resolver is no longer bundled in

package/dist/block.js

@@ -9,7 +9,7 @@
  * never resolves a reference in the first place).
  */
 import { checkKeyLength, checkDuplicateKey, NESTING_DEPTH_LIMIT } from './normalize.js';
-import { stripKeyQuotes, stripComment, stripCommentKeepEscapes, parseQuotedOrTyped, closingQuoteIndex, isValidKey, positionedBuilder, } from './scalars.js';
+import { stripKeyQuotes, stripComment, stripCommentKeepEscapes, parseQuotedOrTyped, closingQuoteIndex, isValidKey, } from './scalars.js';
 import { parseFlowMapping, parseFlowOrScalarValue } from './flow.js';
 import { buildBlockScalar } from './block-scalar.js';
 import { LimaError } from './errors.js';
@@ -49,7 +49,7 @@ const inlineSource = (wantSource, ctx, keyLine, valueCol, rawUndecoded) => wantS
     tabAdjust: ctx.tabAdjust ? [ctx.tabAdjust[keyLine - 1] ?? 0] : undefined,
 }) : undefined;
 const inlineOrBlockScalar = (raw, keyIndent, keyLine, valueCol, rawUndecoded, cursor, ctx, builder) => {
-    const wantSource = builder === positionedBuilder;
+    const wantSource = builder.positions === true;
     if (raw !== '|') {
         const value = parseFlowOrScalarValue(raw, ctx, keyLine, builder, inlineSource(wantSource, ctx, keyLine, valueCol, rawUndecoded));
         cursor.next();
@@ -129,7 +129,7 @@ const cursorAfterDash = (cursor) => {
 };
 /** Shared block grammar consuming one mutable physical-line cursor. */
 const parseCursorBlock = (cursor, baseIndent, ctx, baseLine, builder) => {
-    const wantSource = builder === positionedBuilder;
+    const wantSource = builder.positions === true;
     let items = null;
     let entries = null;
     let pendingItem = null;

package/dist/builder.d.ts

@@ -26,6 +26,8 @@
  */
 import type { ReferenceSource } from './reference-tokens2.js';
 export interface ValueBuilder<V, M = Map<string, V>> {
+    /** Whether scalar builders need physical source anchors for editor positions. */
+    readonly positions?: boolean;
     null(line: number): V;
     bool(value: boolean, line: number): V;
     int(value: number, line: number): V;

package/dist/core.d.ts

@@ -22,6 +22,7 @@ import { type LimaValue } from './value.js';
 import { type ParseContext, type Diagnostic } from './normalize.js';
 import { type PositionedValue } from './scalars.js';
 import type { ValueBuilder } from './builder.js';
+import type { ReferenceToken2 } from './reference-tokens2.js';
 export type { Diagnostic, ParseContext } from './normalize.js';
 export { NESTING_DEPTH_LIMIT, SCALAR_LENGTH_LIMIT } from './normalize.js';
 export type { PositionedValue, InsertedAt } from './scalars.js';
@@ -40,6 +41,16 @@ export type CoreOptions = {
  * primitive the References layer (`references.ts`) builds on.
  */
 export declare const parseCoreWithPositions: (frontMatter: string, ctx: ParseContext) => Map<string, PositionedValue>;
+export type PositionedReferenceParse = {
+    document: Map<string, PositionedValue>;
+    references: ReferenceToken2[];
+};
+/**
+ * Position-aware Core parse plus every active References 2.0 token seen while
+ * values are built. Recording at construction time preserves tokens from
+ * earlier duplicate-key values even though the result map is last-value-wins.
+ */
+export declare const parseCoreWithPositionedReferences: (frontMatter: string, ctx: ParseContext) => PositionedReferenceParse;
 /** The public result shape (Core §11.1): every value `toNative*` can produce. */
 export type NativeValue = null | boolean | number | string | Date | NativeValue[] | {
     [key: string]: NativeValue;

package/dist/core.js

@@ -20,6 +20,7 @@
  */
 import { checkKeyLength, byteLength, DOCUMENT_SIZE_LIMIT, TOP_LEVEL_KEY_LIMIT, NESTING_DEPTH_LIMIT, } from './normalize.js';
 import { unescapeDQ, stripComment, stripCommentKeepEscapes, positionedBuilder, NO_SPAN_VALUE, parseSimpleScalarSpan, } from './scalars.js';
+import { isTrimWhitespace } from './chars.js';
 import { parseFlowOrScalarValue } from './flow.js';
 import { parseBlockRange } from './block.js';
 import { buildBlockScalar } from './block-scalar.js';
@@ -156,8 +157,21 @@ const parseCoreGeneric = (frontMatter, ctx, builder, computeDepth) => {
             searchFrom = lineEnd + 1;
         }
     }
-    const parseEntry = (key, line, rawStart, isBlock, inlineEnd, nextStart) => {
+    const parseEntry = (key, line, separatorEnd, isBlock, inlineEnd, nextStart) => {
         checkKeyLength(key, line);
+        // §4 step 3: an inline value begins after the spaces that follow `: `, however many there are — as in a
+        // block mapping (block.ts trimSlice), so that the scalar paths below and the source column see the value
+        // itself. The newline that ends the line is not skipped.
+        let rawStart = separatorEnd;
+        if (!isBlock) {
+            while (rawStart < nextStart) {
+                const c = frontMatter.charCodeAt(rawStart);
+                // printable ASCII other than SPACE is never whitespace: the common case ends here at once
+                if ((c > 0x20 && c < 0x7f) || c === 10 || !isTrimWhitespace(c))
+                    break;
+                rawStart++;
+            }
+        }
         if ((strict || ctx.onWarning !== undefined) && builder.hasMappingKey(root, key)) {
             const diagnostic = {
                 code: 'DUPLICATE_KEY', line, key,
@@ -176,7 +190,7 @@ const parseCoreGeneric = (frontMatter, ctx, builder, computeDepth) => {
         // source line — the anchor for References 2.0 token positions (§2.4).
         // References 2.0 token positions (§2.4): only build the source anchor
         // for the annotated builder; `parseCore` (native) discards it.
-        const wantSource = builder === positionedBuilder;
+        const wantSource = builder.positions === true;
         const valueLineStart = wantSource ? frontMatter.lastIndexOf('\n', rawStart - 1) + 1 : 0;
         const valueCol = wantSource ? [...frontMatter.slice(valueLineStart, rawStart)].length : 0;
         const lineTabAdjust = wantSource && ctx.tabAdjust ? [ctx.tabAdjust[line - 1] ?? 0] : undefined;
@@ -315,6 +329,28 @@ const parseCoreGeneric = (frontMatter, ctx, builder, computeDepth) => {
  * primitive the References layer (`references.ts`) builds on.
  */
 export const parseCoreWithPositions = (frontMatter, ctx) => parseCoreGeneric(frontMatter, ctx, positionedBuilder, depthOfPositioned);
+/**
+ * Position-aware Core parse plus every active References 2.0 token seen while
+ * values are built. Recording at construction time preserves tokens from
+ * earlier duplicate-key values even though the result map is last-value-wins.
+ */
+export const parseCoreWithPositionedReferences = (frontMatter, ctx) => {
+    const references = [];
+    const recordingBuilder = {
+        ...positionedBuilder,
+        string: (value, line, quoted, source) => {
+            const positioned = positionedBuilder.string(value, line, quoted, source);
+            if (positioned.kind === 'string' && positioned.references2) {
+                references.push(...positioned.references2);
+            }
+            return positioned;
+        },
+    };
+    return {
+        document: parseCoreGeneric(frontMatter, ctx, recordingBuilder, depthOfPositioned),
+        references,
+    };
+};
 /**
  * The `ValueBuilder<NativeValue>` — `parseCore`'s fast path. Every scalar
  * builder is the identity function: unlike `positionedBuilder`, there is no

package/dist/reference-tokens2.d.ts

@@ -39,5 +39,13 @@ export type ReferenceSource = {
     col: number;
     tabAdjust?: number[];
 };
+export declare const SEGMENT = "[a-zA-Z0-9_][a-zA-Z0-9_:-]*";
+export declare const DOC_PATH = "[a-zA-Z0-9_][a-zA-Z0-9_:-]*(?:\\.[a-zA-Z0-9_][a-zA-Z0-9_:-]*)*";
+export declare const PARTIAL_NAME = "[a-zA-Z0-9_][a-zA-Z0-9_:/-]*";
+export declare const PARTIAL_PATH = "[a-zA-Z0-9_][a-zA-Z0-9_:/-]*(?:\\.[a-zA-Z0-9_][a-zA-Z0-9_:-]*)*";
 export declare const PURE_REFERENCE_2: RegExp;
+/** Converts a 0-based codepoint offset to JavaScript/LSP UTF-16 units. */
+export declare const codepointOffsetToUtf16: (text: string, codepointOffset: number) => number;
+/** Converts a 0-based JavaScript/LSP UTF-16 offset to a codepoint offset. */
+export declare const utf16OffsetToCodepoint: (text: string, utf16Offset: number) => number;
 export declare const scanReferenceTokens2: (value: string, source: ReferenceSource | undefined) => ReferenceToken2[];

package/dist/reference-tokens2.js

@@ -1,20 +1,42 @@
 /** Reference tokens recorded while the annotated Core tree is being built. */
-const SEGMENT = '[a-zA-Z0-9_][a-zA-Z0-9_:-]*';
-const DOC_PATH = `${SEGMENT}(?:\\.${SEGMENT})*`;
-const PARTIAL_NAME = '[a-zA-Z0-9_][a-zA-Z0-9_:/-]*';
-const PARTIAL_PATH = `${PARTIAL_NAME}(?:\\.${SEGMENT})*`;
+export const SEGMENT = '[a-zA-Z0-9_][a-zA-Z0-9_:-]*';
+export const DOC_PATH = `${SEGMENT}(?:\\.${SEGMENT})*`;
+export const PARTIAL_NAME = '[a-zA-Z0-9_][a-zA-Z0-9_:/-]*';
+export const PARTIAL_PATH = `${PARTIAL_NAME}(?:\\.${SEGMENT})*`;
 export const PURE_REFERENCE_2 = new RegExp(`^(?:\\$\\{(${DOC_PATH})\\}|\\$\\((${PARTIAL_PATH})\\))$`);
 const REFERENCE_2 = new RegExp(`\\$\\{(${DOC_PATH})\\}|\\$\\((${PARTIAL_PATH})\\)`, 'g');
 const NO_TOKENS = [];
+const utf16WidthAt = (text, offset) => text.codePointAt(offset) > 0xffff ? 2 : 1;
 /** Codepoint length of the UTF-16 slice `[a, b)` of `s`. */
 const codepointLen = (s, a, b) => {
     let n = 0;
     for (let i = a; i < b;) {
-        i += s.codePointAt(i) > 0xffff ? 2 : 1;
+        i += utf16WidthAt(s, i);
         n++;
     }
     return n;
 };
+/** Converts a 0-based codepoint offset to JavaScript/LSP UTF-16 units. */
+export const codepointOffsetToUtf16 = (text, codepointOffset) => {
+    let utf16Offset = 0;
+    let codepoints = 0;
+    while (utf16Offset < text.length && codepoints < codepointOffset) {
+        utf16Offset += utf16WidthAt(text, utf16Offset);
+        codepoints++;
+    }
+    return utf16Offset;
+};
+/** Converts a 0-based JavaScript/LSP UTF-16 offset to a codepoint offset. */
+export const utf16OffsetToCodepoint = (text, utf16Offset) => {
+    let currentUtf16 = 0;
+    let codepoints = 0;
+    const limit = Math.min(Math.max(utf16Offset, 0), text.length);
+    while (currentUtf16 < limit) {
+        currentUtf16 += utf16WidthAt(text, currentUtf16);
+        codepoints++;
+    }
+    return codepoints;
+};
 /** Splice points (decoded value order): token text, UTF-16 index, path. */
 const scanDecoded = (value) => {
     REFERENCE_2.lastIndex = 0;

package/dist/references2.d.ts

@@ -1,5 +1,19 @@
-import { type Diagnostic } from './core.js';
+import { type Diagnostic, type PositionedReferenceParse, type PositionedValue } from './core.js';
 type Meta = Record<string, unknown>;
+/**
+ * Resolve one document-reference path with the same traversal, cycle checks,
+ * and edge budget used by the public References 2.0 parser. The returned
+ * positioned value retains the definition site's source line.
+ */
+export type DocumentReferenceTargetResolution = {
+    status: 'resolved';
+    target: PositionedValue;
+} | {
+    status: 'unverifiable-partials';
+} | {
+    status: 'unresolved';
+};
+export declare const resolveDocumentReferenceTarget: (parsed: PositionedReferenceParse, path: string) => DocumentReferenceTargetResolution;
 export type ParseMode = 'references' | 'core';
 export type ParseOptions = {
     mode?: ParseMode;

package/dist/references2.js

@@ -7,6 +7,10 @@ import { collectAllParticipants, deepCopyPositioned, earliestParticipant, emptyM
 const PARTIAL_NAME = '[a-zA-Z0-9_][a-zA-Z0-9_:/-]*';
 const PARTIAL_NAME_RE = new RegExp(`^${PARTIAL_NAME}$`);
 const MAX_EDGES = 3;
+// Looking up the root path is itself the first reference edge; recursion into
+// that root therefore gets the public resolver's remaining two-edge budget.
+const TARGET_EDGE_BUDGET = MAX_EDGES - 1;
+const referenceResourceStatuses = new WeakMap();
 /** Copies a pure-reference target and stamps the new insertion without
  * discarding provenance already attached to the copied root (R-112). */
 const copyWithInsertion = (target, insertedAt) => {
@@ -44,6 +48,91 @@ const documentTarget = (root, path) => {
     }
     return { root: value, tail: segments.slice(index) };
 };
+export const resolveDocumentReferenceTarget = (parsed, path) => {
+    const { document } = parsed;
+    const target = documentTarget(document, path);
+    if (target === undefined)
+        return { status: 'unresolved' };
+    const resourceStatus = documentReferenceResourceStatus(parsed);
+    if (resourceStatus === 'unverifiable-partials')
+        return { status: resourceStatus };
+    if (resourceStatus === 'invalid')
+        return { status: 'unresolved' };
+    const ctx = { diagnostics: [], cache: new WeakMap() };
+    const stack = new Set([target.root]);
+    const resolved = resolveNode(target.root, document, new Map(), ctx, TARGET_EDGE_BUDGET, stack);
+    if (!resolved.complete || ctx.diagnostics.length > 0)
+        return { status: 'unresolved' };
+    const selected = lookupPath(resolved.value, target.tail);
+    return selected === undefined
+        ? { status: 'unresolved' }
+        : { status: 'resolved', target: selected };
+};
+const resolveDocument = (document, partials, ctx) => {
+    const resolved = new Map();
+    for (const [key, value] of document) {
+        const stack = new Set([value]);
+        resolved.set(key, resolveNode(value, document, partials, ctx, MAX_EDGES, stack).value);
+    }
+    return resolved;
+};
+const assertResolvedDocumentResourceLimits = (resolved) => {
+    const finalized = [...resolved].map(([key, value]) => [key, finalizePositioned(value)]);
+    const depth = finalized.length === 0 ? 0 : Math.max(...finalized.map(([, value]) => value.depth));
+    if (depth > NESTING_DEPTH_LIMIT) {
+        const participants = finalized
+            .filter(([, value]) => value.depth === depth)
+            .flatMap(([, value]) => value.deepestParticipants);
+        const winner = earliestParticipant(participants);
+        throw new LimaError({
+            code: 'RESOURCE_LIMIT', line: winner?.line ?? 1, token: winner?.token,
+            ...(winner?.offset !== undefined ? { column: winner.offset + 1 } : {}),
+            message: `Lima: nesting depth exceeds maximum of ${NESTING_DEPTH_LIMIT} at line ${winner?.line ?? 1}`,
+        });
+    }
+    let nodeCount = 1;
+    for (const [, value] of finalized)
+        nodeCount += value.nodeCount;
+    if (nodeCount > RESULT_NODE_LIMIT) {
+        const participants = [];
+        for (const value of resolved.values())
+            collectAllParticipants(value, participants);
+        const winner = earliestParticipant(participants);
+        throw new LimaError({
+            code: 'RESOURCE_LIMIT', line: winner?.line ?? 1, token: winner?.token,
+            ...(winner?.offset !== undefined ? { column: winner.offset + 1 } : {}),
+            message: `Lima: result exceeds maximum size of ${RESULT_NODE_LIMIT} total nodes at line ${winner?.line ?? 1}`,
+        });
+    }
+    return finalized;
+};
+const documentReferenceResourceStatus = (parsed) => {
+    // Partial values are supplied by caller code and can change whole-document
+    // depth/node limits. With no file convention for them, editor tooling cannot
+    // prove that even an unrelated document reference is safe to resolve.
+    if (parsed.references.some((reference) => reference.partialPath !== undefined))
+        return 'unverifiable-partials';
+    const { document } = parsed;
+    const cached = referenceResourceStatuses.get(document);
+    if (cached !== undefined)
+        return cached;
+    const ctx = { diagnostics: [], cache: new WeakMap() };
+    const resolved = resolveDocument(document, new Map(), ctx);
+    let valid = !ctx.diagnostics.some((diagnostic) => diagnostic.code === 'RESOURCE_LIMIT');
+    if (valid) {
+        try {
+            assertResolvedDocumentResourceLimits(resolved);
+        }
+        catch (error) {
+            if (!(error instanceof LimaError) || error.code !== 'RESOURCE_LIMIT')
+                throw error;
+            valid = false;
+        }
+    }
+    const status = valid ? 'valid' : 'invalid';
+    referenceResourceStatuses.set(document, status);
+    return status;
+};
 const lookupPartial = (partials, path) => {
     const dot = path.indexOf('.');
     if (dot < 0)
@@ -284,11 +373,7 @@ const parseInternal = (frontMatter, options, useResolveCache) => {
     }
     const document = parseCoreWithPositions(frontMatter, { strict: options?.strict ?? false, onWarning: options?.onWarning });
     const ctx = { diagnostics: [], ...(useResolveCache ? { cache: new WeakMap() } : {}) };
-    const resolved = new Map();
-    for (const [key, value] of document) {
-        const stack = new Set([value]);
-        resolved.set(key, resolveNode(value, document, partials, ctx, MAX_EDGES, stack).value);
-    }
+    const resolved = resolveDocument(document, partials, ctx);
     if (options?.strict)
         for (const value of resolved.values())
             scanUnresolved(value, ctx);
@@ -299,31 +384,7 @@ const parseInternal = (frontMatter, options, useResolveCache) => {
         // already do; `offset` was internal-only here.
         throw new LimaError({ ...winner, column: winner.offset + 1 });
     }
-    const finalized = [...resolved].map(([key, value]) => [key, finalizePositioned(value)]);
-    const depth = finalized.length === 0 ? 0 : Math.max(...finalized.map(([, value]) => value.depth));
-    if (depth > NESTING_DEPTH_LIMIT) {
-        const participants = finalized.filter(([, value]) => value.depth === depth).flatMap(([, value]) => value.deepestParticipants);
-        const winner = earliestParticipant(participants);
-        throw new LimaError({
-            code: 'RESOURCE_LIMIT', line: winner?.line ?? 1, token: winner?.token,
-            ...(winner?.offset !== undefined ? { column: winner.offset + 1 } : {}),
-            message: `Lima: nesting depth exceeds maximum of ${NESTING_DEPTH_LIMIT} at line ${winner?.line ?? 1}`,
-        });
-    }
-    let nodeCount = 1;
-    for (const [, value] of finalized)
-        nodeCount += value.nodeCount;
-    if (nodeCount > RESULT_NODE_LIMIT) {
-        const participants = [];
-        for (const value of resolved.values())
-            collectAllParticipants(value, participants);
-        const winner = earliestParticipant(participants);
-        throw new LimaError({
-            code: 'RESOURCE_LIMIT', line: winner?.line ?? 1, token: winner?.token,
-            ...(winner?.offset !== undefined ? { column: winner.offset + 1 } : {}),
-            message: `Lima: result exceeds maximum size of ${RESULT_NODE_LIMIT} total nodes at line ${winner?.line ?? 1}`,
-        });
-    }
+    const finalized = assertResolvedDocumentResourceLimits(resolved);
     const out = emptyMapping();
     for (const [key, value] of finalized)
         out[key] = value.native;

package/dist/scalars.js

@@ -13,6 +13,7 @@ export const hasActiveReferences2 = (value) => value.kind === 'string' ? (value.
         : false;
 /** The `ValueBuilder<PositionedValue>` — reconstructs today's annotated tree exactly, for References. */
 export const positionedBuilder = {
+    positions: true,
     null: (line) => ({ kind: 'null', line }),
     bool: (value, line) => ({ kind: 'bool', value, line }),
     int: (value, line) => ({ kind: 'int', value, line }),

package/package.json

@@ -1,13 +1,13 @@
 {
   "name": "@limaformat/lima",
-  "version": "0.5.0",
+  "version": "0.5.1",
   "description": "Lima frontmatter parser — LIMA Is Metadata Annotation",
   "keywords": ["frontmatter", "parser", "yaml", "markdown", "metadata"],
   "homepage": "https://limaformat.dev",
   "author": "Michael Kortstiege",
   "repository": {
     "type": "git",
-    "url": "https://github.com/limaformat/lima",
+    "url": "git+https://github.com/limaformat/lima.git",
     "directory": "js"
   },
   "bugs": "https://github.com/limaformat/lima/issues",