Files
inline-schema/src/csv-loader/reference-resolver.ts
T
hypercross 6da2815301 refactor: decouple table loading from lookup generation
Extract `loadReferenceTableData` to separate the raw file loading
logic from the primary key lookup construction. This prevents
unnecessary Map creation during reverse reference resolution.
2026-08-06 10:42:10 +08:00

540 lines
15 KiB
TypeScript

import * as fs from "fs";
import * as path from "path";
import { parseValue } from "../index.js";
import type {
Schema,
ReferenceSchema,
ReverseReferenceSchema,
} from "../types.js";
import type { ReferenceFieldInfo } from "./types.js";
import { parseCsv } from "./loader.js";
/** Cache for loaded referenced tables */
const referenceTableCache = new Map<string, Record<string, unknown>[]>();
/**
* Cache for reverse-reference lookups: filePath -> (foreignKey -> (fkValue -> rows[])).
* Built once per referenced table + foreign key, mirroring what module-gen emits,
* so resolveReverseReference doesn't re-filter the whole table per row.
*/
const reverseLookupCache = new Map<
string,
Map<string, Map<string, Record<string, unknown>[]>>
>();
/** Set of file paths currently being loaded (to detect circular references) */
const loadingFiles = new Set<string>();
export function hasNestedReferences(schema: Schema): boolean {
switch (schema.type) {
case "reference":
case "reverseReference":
return true;
case "tuple":
return schema.elements.some((el) => hasNestedReferences(el.schema));
case "array":
return hasNestedReferences(schema.element);
case "union":
return schema.members.some((m) => hasNestedReferences(m));
default:
return false;
}
}
function loadReferenceTableData(
schema: ReferenceSchema | ReverseReferenceSchema,
refBaseDir: string | undefined,
currentFilePath: string | undefined,
): {
refTable: Record<string, unknown>[];
refFilePath: string;
} {
const baseDir =
refBaseDir ||
(currentFilePath ? path.dirname(currentFilePath) : process.cwd());
const fileName = `${schema.tableName}.csv`;
const refFilePath = path.isAbsolute(fileName)
? fileName
: path.join(baseDir, fileName);
let refTable: Record<string, unknown>[];
if (referenceTableCache.has(refFilePath)) {
refTable = referenceTableCache.get(refFilePath)!;
} else {
if (loadingFiles.has(refFilePath)) {
throw new Error(
`Circular reference detected: table "${schema.tableName}" (${refFilePath}) is already being loaded`,
);
}
loadingFiles.add(refFilePath);
try {
const refContent = fs.readFileSync(refFilePath, "utf-8");
const refResult = parseCsv(refContent, {
currentFilePath: refFilePath,
emitTypes: false,
});
refTable = refResult.data;
referenceTableCache.set(refFilePath, refTable);
} catch (error) {
throw new Error(
`Failed to load referenced table "${schema.tableName}" from ${refFilePath}: ${error instanceof Error ? error.message : String(error)}`,
);
} finally {
loadingFiles.delete(refFilePath);
}
}
return { refTable, refFilePath };
}
/**
* Load a referenced table and build a forward lookup keyed by primary key.
* Only call this when forward resolution is actually needed; the reverse
* path uses `loadReferenceTableData` directly to avoid building a throwaway map.
*/
export function loadReferenceTable(
schema: ReferenceSchema | ReverseReferenceSchema,
refBaseDir: string | undefined,
defaultPrimaryKey: string,
currentFilePath: string | undefined,
): {
lookup: Map<string, Record<string, unknown>>;
refTable: Record<string, unknown>[];
refFilePath: string;
} {
const { refTable, refFilePath } = loadReferenceTableData(
schema,
refBaseDir,
currentFilePath,
);
const lookup = new Map<string, Record<string, unknown>>();
refTable.forEach((row) => {
const pkValue = row[defaultPrimaryKey];
if (pkValue !== undefined) {
lookup.set(String(pkValue), row);
}
});
return { lookup, refTable, refFilePath };
}
/**
* Build (and cache) a reverse lookup for a referenced table + foreign key:
* a map from the foreign-key value to the rows that reference it.
*/
function getReverseLookup(
schema: ReverseReferenceSchema,
refBaseDir: string | undefined,
defaultPrimaryKey: string,
currentFilePath: string | undefined,
): Map<string, Record<string, unknown>[]> {
const { refTable, refFilePath } = loadReferenceTableData(
schema,
refBaseDir,
currentFilePath,
);
let byForeignKey = reverseLookupCache.get(refFilePath);
if (!byForeignKey) {
byForeignKey = new Map();
reverseLookupCache.set(refFilePath, byForeignKey);
}
const cached = byForeignKey.get(schema.foreignKey);
if (cached) return cached;
const lookup = new Map<string, Record<string, unknown>[]>();
for (const row of refTable) {
const fkValue = row[schema.foreignKey];
const fkStr =
fkValue !== null && fkValue !== undefined && typeof fkValue === "object"
? String((fkValue as Record<string, unknown>)[defaultPrimaryKey])
: String(fkValue);
const bucket = lookup.get(fkStr);
if (bucket) {
bucket.push(row);
} else {
lookup.set(fkStr, [row]);
}
}
byForeignKey.set(schema.foreignKey, lookup);
return lookup;
}
export function resolveReferenceId(
id: string,
lookup: Map<string, Record<string, unknown>>,
tableName: string,
): Record<string, unknown> {
const obj = lookup.get(id);
if (!obj) {
throw new Error(`Reference to "${tableName}" with id="${id}" not found`);
}
return obj;
}
export function parseReferenceIds(
schema: ReferenceSchema,
valueString: string,
): unknown {
const trimmed = valueString.trim();
if (schema.isOptional && trimmed === "") {
return null;
}
return parseValue(schema, trimmed);
}
export function parseValueWithReferenceIds(
valueString: string,
schema: Schema,
): unknown {
if (!hasNestedReferences(schema)) {
return parseValue(schema, valueString);
}
switch (schema.type) {
case "reference":
return parseReferenceIds(schema, valueString);
case "reverseReference":
// Reverse references don't store IDs; they're derived at resolution time
return null;
case "tuple": {
const parsed = parseValue(schema, valueString) as unknown[];
return schema.elements.map((el, i) =>
hasNestedReferences(el.schema)
? extractNestedReferenceIds(parsed[i], el.schema)
: parsed[i],
);
}
case "array": {
const parsed = parseValue(schema, valueString) as unknown[];
return parsed.map((item) =>
hasNestedReferences(schema.element)
? extractNestedReferenceIds(item, schema.element)
: item,
);
}
case "union": {
for (const member of schema.members) {
if (hasNestedReferences(member)) {
try {
const parsed = parseValue(member, valueString);
return extractNestedReferenceIds(parsed, member);
} catch {}
}
}
return parseValue(schema, valueString);
}
default:
return parseValue(schema, valueString);
}
}
export function extractNestedReferenceIds(
value: unknown,
schema: Schema,
): unknown {
switch (schema.type) {
case "reference":
if (value === null || value === undefined) return value;
if (schema.isArray) {
const ids = Array.isArray(value) ? value : [value];
return ids.map((id) => String(id));
}
return String(value);
case "reverseReference":
// Reverse references don't store IDs; return null placeholder
return null;
case "tuple": {
if (!Array.isArray(value)) return value;
return schema.elements.map((el, i) =>
hasNestedReferences(el.schema)
? extractNestedReferenceIds(value[i], el.schema)
: value[i],
);
}
case "array": {
if (!Array.isArray(value)) return value;
return value.map((item) =>
hasNestedReferences(schema.element)
? extractNestedReferenceIds(item, schema.element)
: item,
);
}
case "union": {
for (const member of schema.members) {
if (hasNestedReferences(member)) {
try {
return extractNestedReferenceIds(value, member);
} catch {}
}
}
return value;
}
default:
return value;
}
}
export function collectReferenceFields(
schema: Schema,
name: string,
): ReferenceFieldInfo[] {
const fields: ReferenceFieldInfo[] = [];
switch (schema.type) {
case "reference":
fields.push({
name,
tableName: schema.tableName,
isArray: schema.isArray,
schema,
});
break;
case "reverseReference":
fields.push({
name,
tableName: schema.tableName,
isArray: true,
foreignKey: schema.foreignKey,
schema,
});
break;
case "tuple":
for (const el of schema.elements) {
fields.push(...collectReferenceFields(el.schema, name));
}
break;
case "array":
fields.push(...collectReferenceFields(schema.element, name));
break;
case "union":
for (const member of schema.members) {
fields.push(...collectReferenceFields(member, name));
}
break;
}
return fields;
}
export function parseValueWithReferences(
valueString: string,
schema: Schema,
refBaseDir: string | undefined,
defaultPrimaryKey: string,
currentFilePath: string | undefined,
currentRowPk?: unknown,
): unknown {
if (!hasNestedReferences(schema)) {
return parseValue(schema, valueString);
}
switch (schema.type) {
case "reference":
return parseReferenceValue(
schema,
valueString,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
);
case "reverseReference": {
if (currentRowPk === undefined) return [];
return resolveReverseReference(
schema,
currentRowPk,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
);
}
case "tuple": {
const parsed = parseValue(schema, valueString) as unknown[];
return schema.elements.map((el, i) =>
resolveNestedReferences(
parsed[i],
el.schema,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
currentRowPk,
),
);
}
case "array": {
const parsed = parseValue(schema, valueString) as unknown[];
return parsed.map((item) =>
resolveNestedReferences(
item,
schema.element,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
currentRowPk,
),
);
}
case "union": {
// Try reference members first (more specific), then non-reference members.
// This makes the fallback structural rather than error-message-driven.
const refMembers = schema.members.filter(hasNestedReferences);
const nonRefMembers = schema.members.filter((m) => !hasNestedReferences(m));
const errors: Error[] = [];
for (const member of [...refMembers, ...nonRefMembers]) {
try {
const parsed = parseValue(member, valueString);
return resolveNestedReferences(
parsed,
member,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
currentRowPk,
);
} catch (e) {
errors.push(e instanceof Error ? e : new Error(String(e)));
}
}
throw errors[0] ?? new Error("Value does not match any union member");
}
default:
return parseValue(schema, valueString);
}
}
export function resolveReverseReference(
schema: ReverseReferenceSchema,
pkValue: unknown,
refBaseDir: string | undefined,
defaultPrimaryKey: string,
currentFilePath: string | undefined,
): Record<string, unknown>[] {
const lookup = getReverseLookup(
schema,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
);
return lookup.get(String(pkValue)) ?? [];
}
export function resolveNestedReferences(
value: unknown,
schema: Schema,
refBaseDir: string | undefined,
defaultPrimaryKey: string,
currentFilePath: string | undefined,
currentRowPk?: unknown,
): unknown {
switch (schema.type) {
case "reference": {
if (value === null || value === undefined) return value;
const { lookup } = loadReferenceTable(
schema,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
);
if (schema.isArray) {
const ids = Array.isArray(value) ? value : [value];
return ids.map((id) =>
resolveReferenceId(String(id), lookup, schema.tableName),
);
}
return resolveReferenceId(String(value), lookup, schema.tableName);
}
case "reverseReference": {
if (currentRowPk === undefined) return [];
const results = resolveReverseReference(
schema,
currentRowPk,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
);
return results;
}
case "tuple": {
if (!Array.isArray(value)) return value;
return schema.elements.map((el, i) =>
resolveNestedReferences(
value[i],
el.schema,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
currentRowPk,
),
);
}
case "array": {
if (!Array.isArray(value)) return value;
return value.map((item) =>
resolveNestedReferences(
item,
schema.element,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
currentRowPk,
),
);
}
case "union": {
// Try reference members first (more specific), then non-reference members.
const refMembers = schema.members.filter(hasNestedReferences);
const nonRefMembers = schema.members.filter((m) => !hasNestedReferences(m));
const errors: Error[] = [];
for (const member of [...refMembers, ...nonRefMembers]) {
try {
return resolveNestedReferences(
value,
member,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
currentRowPk,
);
} catch (e) {
errors.push(e instanceof Error ? e : new Error(String(e)));
}
}
if (errors.length > 0) {
throw errors[0];
}
return value;
}
default:
return value;
}
}
export function parseReferenceValue(
schema: ReferenceSchema,
valueString: string,
refBaseDir: string | undefined,
defaultPrimaryKey: string,
currentFilePath: string | undefined,
): unknown {
const trimmed = valueString.trim();
if (schema.isOptional && trimmed === "") {
return null;
}
const { lookup } = loadReferenceTable(
schema,
refBaseDir,
defaultPrimaryKey,
currentFilePath,
);
const ids = parseValue(schema, trimmed) as string | string[] | null;
if (ids === null) return null;
if (schema.isArray && Array.isArray(ids)) {
return ids.map((id) => resolveReferenceId(id, lookup, schema.tableName));
}
return resolveReferenceId(ids as string, lookup, schema.tableName);
}