mirror of
https://github.com/morluto/rea.git
synced 2026-11-16 11:43:20 +00:00
refactor(domain): give strict UTF-8 decoding one owner with an explicit BOM policy (#10728)
* refactor(domain): give strict UTF-8 decoding one owner with an explicit BOM policy * fix(domain): keep the leading-BOM behaviour every migrated UTF-8 decoder had * refactor(domain): read the domain layer's strict UTF-8 through the BOM-policy owner (#10803) Twelve domain decoders built their own fatal TextDecoder with ignoreBOM: true. They now use strictUtf8Decoder("preserve"), which keeps that behaviour: each reads bytes where a leading U+FEFF is content (binary-format names and fields, JSON and XML read byte-for-byte, recorded bodies, registry seeds whose kept bytes are re-emitted). The counted baseline drops from 74 to 62. * refactor(artifacts): read artifact readers' strict UTF-8 through the BOM-policy owner (#10871) Fourteen artifact reader modules (17 sites) built their own fatal TextDecoder. They now take it from strictUtf8Decoder with the policy each had: every one kept a leading BOM (ignoreBOM: true), so they use "preserve"; JavaScriptArtifactFiles keeps it for JavaScript and HTML entries and strips it otherwise, as before. The strict-utf8-decoder baseline drops those 17 sites. * refactor(domain): drop TextDecoder imports left by the strict UTF-8 migration * refactor(application): read MCP registration metadata through the strict UTF-8 owner * refactor(formats): read binary-format readers' strict UTF-8 through the BOM-policy owner (#10903) * refactor(formats): read binary-format readers' strict UTF-8 through the BOM-policy owner * refactor(formats): drop the model readers' unused TextDecoder imports * refactor(browser): read browser capture and fetch strict UTF-8 through the BOM-policy owner (#10935) * refactor(browser): read browser capture and fetch strict UTF-8 through the BOM-policy owner * refactor(native): read LLDB and Mach-O name strict UTF-8 through the BOM-policy owner (#10936) * refactor(native): read LLDB and Mach-O name strict UTF-8 through the BOM-policy owner * refactor(process): read MCP and NDJSON transport frames' strict UTF-8 through the BOM-policy owner (#10937) * refactor(process): read MCP and NDJSON transport frames' strict UTF-8 through the BOM-policy owner * refactor(application): read JSON and file inputs' strict UTF-8 through the BOM-policy owner (#10938) * refactor(application): read JSON and file inputs' strict UTF-8 through the BOM-policy owner * refactor(providers): read IDA, Electron, Ghidra and reference strict UTF-8 through the BOM-policy owner (#10939) * refactor(providers): read IDA, Electron, Ghidra and reference strict UTF-8 through the BOM-policy owner * refactor(evm): read the hex bytecode carrier's strict UTF-8 through the owner and refuse new local decoders (#10940) * refactor(evm): read the hex bytecode carrier's strict UTF-8 through the BOM-policy owner * chore(architecture): match local strict UTF-8 decoders in any option order
This commit is contained in:
1 parent
abd36dd250
commit
cabd56ea71
103 files changed
+322
-251
No files matched your search
@@ -1,3 +1,4 @@
|
||||
import { strictUtf8Decoder } from "../domain/strictUtf8.js";
|
||||
import {
|
||||
checkRange,
|
||||
checkedSectionCount,
|
||||
@@ -355,7 +356,7 @@ const createStringReader = (
|
||||
) => {
|
||||
const stringEnd = strings.offset + strings.size;
|
||||
const pool = bytes.subarray(strings.offset, stringEnd);
|
||||
const decoder = new TextDecoder("utf-8", { fatal: true, ignoreBOM: true });
|
||||
const decoder = strictUtf8Decoder("preserve");
|
||||
const cache = new Map<number, string>();
|
||||
return (index: number, label: string) => {
|
||||
const cached = cache.get(index);
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { strictUtf8Decoder } from "../domain/strictUtf8.js";
|
||||
import type { Il2cppMetadata } from "../domain/il2cpp/il2cppMetadata.js";
|
||||
import {
|
||||
checkRange,
|
||||
@@ -141,7 +142,7 @@ function* readStringLiterals(
|
||||
const { bytes, section, indexing, members } = tables;
|
||||
const literals = section("stringLiterals"),
|
||||
data = section("stringLiteralData");
|
||||
const decoder = new TextDecoder("utf-8", { fatal: true, ignoreBOM: true });
|
||||
const decoder = strictUtf8Decoder("preserve");
|
||||
// Repeated spans reuse their decoded text for this immutable file snapshot.
|
||||
const decoded = new Map<string, Members["string_literals"][number]>();
|
||||
const rows: Members["string_literals"] = [];
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { strictUtf8Decoder } from "../domain/strictUtf8.js";
|
||||
import { IL2CPP_METADATA_SECTION_NAMES } from "../domain/il2cpp/il2cppMetadata.js";
|
||||
import { observeIl2cppMetadataHeaderPrefix } from "../domain/il2cpp/il2cppMetadataHeaderPrefix.js";
|
||||
import { Il2cppMetadataFormatFailure } from "./Il2cppMetadataFormat.js";
|
||||
@@ -23,7 +24,7 @@ const HEADER_BYTES = 8 + SECTION_NAMES.length * 12;
|
||||
const SAMPLE_STRINGS = 16;
|
||||
const SAMPLE_BYTES = 128;
|
||||
const SCAN_BATCH_BYTES = 64 * 1024;
|
||||
const utf8 = new TextDecoder("utf-8", { fatal: true, ignoreBOM: true });
|
||||
const utf8 = strictUtf8Decoder("preserve");
|
||||
|
||||
/** A bounded, header-only observation; never a decoded metadata report. */
|
||||
export const inspectIl2cppMetadataV108 = async (
|
||||
|
||||
Reference in new issue
Block a user