Compare commits

..

70 Commits

Author SHA1 Message Date
5cc030d433 v5.0.0 2025-11-25 12:32:13 +00:00
2b91c1586c BREAKING CHANGE(SmartArchive): Refactor public API: rename factory/extraction methods, introduce typed interfaces and improved compression tools 2025-11-25 12:32:13 +00:00
e609c023bc v4.2.4 2025-11-25 11:59:11 +00:00
634c204a00 fix(plugins): Migrate filesystem usage to Node fs/fsPromises and upgrade smartfile to v13; add listFileTree helper and update tests 2025-11-25 11:59:11 +00:00
7ccd210c45 v4.2.3 2025-11-25 11:28:31 +00:00
fe90de56d6 fix(build): Upgrade dev tooling: bump @git.zone/tsbuild, @git.zone/tsrun and @git.zone/tstest versions 2025-11-25 11:28:31 +00:00
d9251fa1a5 4.2.2 2025-08-18 02:06:31 +00:00
ec58b9cdc5 fix(smartarchive): Improve tar entry streaming handling and add in-memory gzip/tgz tests 2025-08-18 02:06:31 +00:00
9dbb7d9731 4.2.1 2025-08-18 01:52:21 +00:00
4428638170 fix(gzip): Improve gzip streaming decompression, archive analysis and unpacking; add gzip tests 2025-08-18 01:52:20 +00:00
1af585594c 4.2.0 2025-08-18 01:29:06 +00:00
780db4921e feat(classes.smartarchive): Support URL streams, recursive archive unpacking and filesystem export; improve ZIP/GZIP/BZIP2 robustness; CI and package metadata updates 2025-08-18 01:29:06 +00:00
ed5f590b5f 4.1.0 2025-08-18 01:01:02 +00:00
a32ed0facd feat(classes.smartarchive): Support URL web streams, add recursive archive unpacking and filesystem export, and improve ZIP decompression robustness 2025-08-18 01:01:02 +00:00
b5a3793ed5 fix: update import path for tapbundle and refactor download logic
- Changed the import path for tapbundle from '@push.rocks/tapbundle' to '@git.zone/tstest/tapbundle'.
- Refactored the download logic in the preTask for preparing downloads to use SmartRequest for better handling of the response.
- Added a new pnpm workspace configuration file to specify only built dependencies.
2025-08-18 00:47:24 +00:00
be1bc958d8 4.0.39 2024-10-13 13:25:52 +02:00
21434622dd fix(core): Fix dependencies and update documentation. 2024-10-13 13:25:52 +02:00
50c0368ac7 4.0.38 2024-10-13 13:24:06 +02:00
78b3fcfd83 fix(dependencies): Update dependencies to latest versions 2024-10-13 13:24:05 +02:00
61caf51f4e 4.0.37 2024-06-08 14:48:25 +02:00
be4e2cdae7 fix(core): update 2024-06-08 14:48:24 +02:00
1cb8331666 4.0.36 2024-06-08 14:01:26 +02:00
aa203c5ab2 fix(core): update 2024-06-08 14:01:25 +02:00
87aedd5ef5 4.0.35 2024-06-08 14:00:56 +02:00
64431703b5 fix(core): update 2024-06-08 14:00:55 +02:00
120fd0b321 4.0.34 2024-06-08 13:47:39 +02:00
e6192c418e fix(core): update 2024-06-08 13:47:38 +02:00
00a039936f 4.0.33 2024-06-08 12:49:03 +02:00
e03c3a62b1 fix(core): update 2024-06-08 12:49:02 +02:00
538eced73b 4.0.32 2024-06-08 12:46:44 +02:00
fe8a5713f0 fix(core): update 2024-06-08 12:46:43 +02:00
37e8a1d0f7 4.0.31 2024-06-08 12:44:41 +02:00
5143cd098d fix(core): update 2024-06-08 12:44:40 +02:00
4d5ea812af 4.0.30 2024-06-08 12:40:57 +02:00
500ef01ded fix(core): update 2024-06-08 12:40:56 +02:00
3196a02835 4.0.29 2024-06-08 11:06:10 +02:00
de1c46ed0a fix(core): update 2024-06-08 11:06:09 +02:00
b4c7b065fa 4.0.28 2024-06-08 11:03:38 +02:00
93da11a951 fix(core): update 2024-06-08 11:03:37 +02:00
ecd7f6d419 4.0.27 2024-06-08 11:01:56 +02:00
a3ecfe4d99 fix(core): update 2024-06-08 11:01:56 +02:00
f99f6d96c5 4.0.26 2024-06-08 10:47:28 +02:00
b4be70f43a fix(core): update 2024-06-08 10:47:27 +02:00
785e26e72d 4.0.25 2024-06-08 10:30:05 +02:00
e1891a6aa3 fix(core): update 2024-06-08 10:30:03 +02:00
f257c0c5a4 4.0.24 2024-06-06 20:59:05 +02:00
725546e409 fix(core): update 2024-06-06 20:59:04 +02:00
b9645dfb99 4.0.23 2024-06-06 20:48:03 +02:00
b860aca103 fix(core): update 2024-06-06 20:48:02 +02:00
39fb6e8ad1 update description 2024-05-29 14:11:45 +02:00
04968a80b0 update tsconfig 2024-04-14 17:20:20 +02:00
e4a2c143bc update npmextra.json: githost 2024-04-01 21:33:47 +02:00
ed6d186a85 update npmextra.json: githost 2024-04-01 19:57:39 +02:00
553c5dfe99 update npmextra.json: githost 2024-03-30 21:46:35 +01:00
5d94efb9ee 4.0.22 2024-03-17 00:42:19 +01:00
c978ca107b fix(core): update 2024-03-17 00:42:19 +01:00
876c8ce9d8 4.0.21 2024-03-17 00:35:18 +01:00
7327bf1bd0 fix(core): update 2024-03-17 00:35:17 +01:00
2dcb10d233 4.0.20 2024-03-17 00:29:42 +01:00
d53c46fa82 fix(core): update 2024-03-17 00:29:42 +01:00
25e847a9ea 4.0.19 2023-11-14 13:17:06 +01:00
cc0ecb3f16 fix(core): update 2023-11-14 13:17:05 +01:00
2cd0846c74 4.0.18 2023-11-14 10:58:02 +01:00
49ab40af09 fix(core): update 2023-11-14 10:58:01 +01:00
5ff51ff88d 4.0.17 2023-11-14 10:55:20 +01:00
c578a3fdc1 fix(core): update 2023-11-14 10:55:19 +01:00
ad0352a712 4.0.16 2023-11-13 23:14:39 +01:00
f921338fd6 fix(core): update 2023-11-13 23:14:39 +01:00
614dae5ade 4.0.15 2023-11-13 22:11:25 +01:00
f87359fb97 fix(core): update 2023-11-13 22:11:24 +01:00
35 changed files with 18758 additions and 5341 deletions

View File

@@ -6,8 +6,8 @@ on:
- '**' - '**'
env: env:
IMAGE: registry.gitlab.com/hosttoday/ht-docker-node:npmci IMAGE: code.foss.global/host.today/ht-docker-node:npmci
NPMCI_COMPUTED_REPOURL: https://${{gitea.repository_owner}}:${{secrets.GITEA_TOKEN}}@gitea.lossless.digital/${{gitea.repository}}.git NPMCI_COMPUTED_REPOURL: https://${{gitea.repository_owner}}:${{secrets.GITEA_TOKEN}}@/${{gitea.repository}}.git
NPMCI_TOKEN_NPM: ${{secrets.NPMCI_TOKEN_NPM}} NPMCI_TOKEN_NPM: ${{secrets.NPMCI_TOKEN_NPM}}
NPMCI_TOKEN_NPM2: ${{secrets.NPMCI_TOKEN_NPM2}} NPMCI_TOKEN_NPM2: ${{secrets.NPMCI_TOKEN_NPM2}}
NPMCI_GIT_GITHUBTOKEN: ${{secrets.NPMCI_GIT_GITHUBTOKEN}} NPMCI_GIT_GITHUBTOKEN: ${{secrets.NPMCI_GIT_GITHUBTOKEN}}
@@ -26,7 +26,7 @@ jobs:
- name: Install pnpm and npmci - name: Install pnpm and npmci
run: | run: |
pnpm install -g pnpm pnpm install -g pnpm
pnpm install -g @shipzone/npmci pnpm install -g @ship.zone/npmci
- name: Run npm prepare - name: Run npm prepare
run: npmci npm prepare run: npmci npm prepare

View File

@@ -6,8 +6,8 @@ on:
- '*' - '*'
env: env:
IMAGE: registry.gitlab.com/hosttoday/ht-docker-node:npmci IMAGE: code.foss.global/host.today/ht-docker-node:npmci
NPMCI_COMPUTED_REPOURL: https://${{gitea.repository_owner}}:${{secrets.GITEA_TOKEN}}@gitea.lossless.digital/${{gitea.repository}}.git NPMCI_COMPUTED_REPOURL: https://${{gitea.repository_owner}}:${{secrets.GITEA_TOKEN}}@/${{gitea.repository}}.git
NPMCI_TOKEN_NPM: ${{secrets.NPMCI_TOKEN_NPM}} NPMCI_TOKEN_NPM: ${{secrets.NPMCI_TOKEN_NPM}}
NPMCI_TOKEN_NPM2: ${{secrets.NPMCI_TOKEN_NPM2}} NPMCI_TOKEN_NPM2: ${{secrets.NPMCI_TOKEN_NPM2}}
NPMCI_GIT_GITHUBTOKEN: ${{secrets.NPMCI_GIT_GITHUBTOKEN}} NPMCI_GIT_GITHUBTOKEN: ${{secrets.NPMCI_GIT_GITHUBTOKEN}}
@@ -26,7 +26,7 @@ jobs:
- name: Prepare - name: Prepare
run: | run: |
pnpm install -g pnpm pnpm install -g pnpm
pnpm install -g @shipzone/npmci pnpm install -g @ship.zone/npmci
npmci npm prepare npmci npm prepare
- name: Audit production dependencies - name: Audit production dependencies
@@ -54,7 +54,7 @@ jobs:
- name: Prepare - name: Prepare
run: | run: |
pnpm install -g pnpm pnpm install -g pnpm
pnpm install -g @shipzone/npmci pnpm install -g @ship.zone/npmci
npmci npm prepare npmci npm prepare
- name: Test stable - name: Test stable
@@ -82,7 +82,7 @@ jobs:
- name: Prepare - name: Prepare
run: | run: |
pnpm install -g pnpm pnpm install -g pnpm
pnpm install -g @shipzone/npmci pnpm install -g @ship.zone/npmci
npmci npm prepare npmci npm prepare
- name: Release - name: Release
@@ -104,7 +104,7 @@ jobs:
- name: Prepare - name: Prepare
run: | run: |
pnpm install -g pnpm pnpm install -g pnpm
pnpm install -g @shipzone/npmci pnpm install -g @ship.zone/npmci
npmci npm prepare npmci npm prepare
- name: Code quality - name: Code quality

7
.gitignore vendored
View File

@@ -3,7 +3,6 @@
# artifacts # artifacts
coverage/ coverage/
public/ public/
pages/
# installs # installs
node_modules/ node_modules/
@@ -17,4 +16,8 @@ node_modules/
dist/ dist/
dist_*/ dist_*/
# custom # AI
.claude/
.serena/
#------# custom

Binary file not shown.

68
.serena/project.yml Normal file
View File

@@ -0,0 +1,68 @@
# language of the project (csharp, python, rust, java, typescript, go, cpp, or ruby)
# * For C, use cpp
# * For JavaScript, use typescript
# Special requirements:
# * csharp: Requires the presence of a .sln file in the project folder.
language: typescript
# whether to use the project's gitignore file to ignore files
# Added on 2025-04-07
ignore_all_files_in_gitignore: true
# list of additional paths to ignore
# same syntax as gitignore, so you can use * and **
# Was previously called `ignored_dirs`, please update your config if you are using that.
# Added (renamed) on 2025-04-07
ignored_paths: []
# whether the project is in read-only mode
# If set to true, all editing tools will be disabled and attempts to use them will result in an error
# Added on 2025-04-18
read_only: false
# list of tool names to exclude. We recommend not excluding any tools, see the readme for more details.
# Below is the complete list of tools for convenience.
# To make sure you have the latest list of tools, and to view their descriptions,
# execute `uv run scripts/print_tool_overview.py`.
#
# * `activate_project`: Activates a project by name.
# * `check_onboarding_performed`: Checks whether project onboarding was already performed.
# * `create_text_file`: Creates/overwrites a file in the project directory.
# * `delete_lines`: Deletes a range of lines within a file.
# * `delete_memory`: Deletes a memory from Serena's project-specific memory store.
# * `execute_shell_command`: Executes a shell command.
# * `find_referencing_code_snippets`: Finds code snippets in which the symbol at the given location is referenced.
# * `find_referencing_symbols`: Finds symbols that reference the symbol at the given location (optionally filtered by type).
# * `find_symbol`: Performs a global (or local) search for symbols with/containing a given name/substring (optionally filtered by type).
# * `get_current_config`: Prints the current configuration of the agent, including the active and available projects, tools, contexts, and modes.
# * `get_symbols_overview`: Gets an overview of the top-level symbols defined in a given file.
# * `initial_instructions`: Gets the initial instructions for the current project.
# Should only be used in settings where the system prompt cannot be set,
# e.g. in clients you have no control over, like Claude Desktop.
# * `insert_after_symbol`: Inserts content after the end of the definition of a given symbol.
# * `insert_at_line`: Inserts content at a given line in a file.
# * `insert_before_symbol`: Inserts content before the beginning of the definition of a given symbol.
# * `list_dir`: Lists files and directories in the given directory (optionally with recursion).
# * `list_memories`: Lists memories in Serena's project-specific memory store.
# * `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building).
# * `prepare_for_new_conversation`: Provides instructions for preparing for a new conversation (in order to continue with the necessary context).
# * `read_file`: Reads a file within the project directory.
# * `read_memory`: Reads the memory with the given name from Serena's project-specific memory store.
# * `remove_project`: Removes a project from the Serena configuration.
# * `replace_lines`: Replaces a range of lines within a file with new content.
# * `replace_symbol_body`: Replaces the full definition of a symbol.
# * `restart_language_server`: Restarts the language server, may be necessary when edits not through Serena happen.
# * `search_for_pattern`: Performs a search for a pattern in the project.
# * `summarize_changes`: Provides instructions for summarizing the changes made to the codebase.
# * `switch_modes`: Activates modes by providing a list of their names
# * `think_about_collected_information`: Thinking tool for pondering the completeness of collected information.
# * `think_about_task_adherence`: Thinking tool for determining whether the agent is still on track with the current task.
# * `think_about_whether_you_are_done`: Thinking tool for determining whether the task is truly completed.
# * `write_memory`: Writes a named memory (for future reference) to Serena's project-specific memory store.
excluded_tools: []
# initial prompt for the project. It will always be given to the LLM upon activating the project
# (contrary to the memories, which are loaded on demand).
initial_prompt: ""
project_name: "smartarchive"

135
changelog.md Normal file
View File

@@ -0,0 +1,135 @@
# Changelog
## 2025-11-25 - 5.0.0 - BREAKING CHANGE(SmartArchive)
Refactor public API: rename factory/extraction methods, introduce typed interfaces and improved compression tools
- Renamed SmartArchive factory methods: fromArchiveUrl -> fromUrl, fromArchiveFile -> fromFile, fromArchiveStream -> fromStream; added fromBuffer helper.
- Renamed extraction APIs: exportToFs -> extractToDirectory and exportToStreamOfStreamFiles -> extractToStream; stream-based helpers updated accordingly.
- Export surface reorganized (ts/index.ts): core interfaces and errors are exported and new modules (bzip2tools, archiveanalyzer) are publicly available.
- Introduced strong TypeScript types (ts/interfaces.ts) and centralized error types (ts/errors.ts) including Bzip2Error and BZIP2_ERROR_CODES.
- Refactored format implementations and stream transforms: GzipTools/GzipCompressionTransform/GzipDecompressionTransform, ZipTools (ZipCompressionStream, ZipDecompressionTransform), TarTools improvements.
- BZIP2 implementation improvements: new bit iterator (IBitReader), clearer error handling and streaming unbzip2 transform.
- Updated tests to use the new APIs and method names.
- Breaking change: public API method names and some class/transform names have changed — this requires code updates for consumers.
## 2025-11-25 - 4.2.4 - fix(plugins)
Migrate filesystem usage to Node fs/fsPromises and upgrade smartfile to v13; add listFileTree helper and update tests
- Bumped dependency @push.rocks/smartfile to ^13.0.0 and removed unused dependency `through`
- Replaced usages of smartfile.fs and smartfile.fsStream with Node native fs and fs/promises (createReadStream/createWriteStream, mkdir({recursive:true}), stat, readFile)
- Added plugins.listFileTree helper (recursive directory lister) and used it in TarTools.packDirectory and tests
- Updated SmartArchive.exportToFs to use plugins.fs and plugins.fsPromises for directory creation and file writes
- Updated TarTools to use plugins.fs.createReadStream and plugins.fsPromises.stat when packing directories
- Converted/updated tests to a Node/Deno-friendly test file (test.node+deno.ts) and switched test helpers to use fsPromises
- Added readme.hints.md with migration notes for Smartfile v13 and architecture/dependency notes
## 2025-11-25 - 4.2.3 - fix(build)
Upgrade dev tooling: bump @git.zone/tsbuild, @git.zone/tsrun and @git.zone/tstest versions
- Bump @git.zone/tsbuild from ^2.6.6 to ^3.1.0
- Bump @git.zone/tsrun from ^1.3.3 to ^2.0.0
- Bump @git.zone/tstest from ^2.3.4 to ^3.1.3
## 2025-08-18 - 4.2.2 - fix(smartarchive)
Improve tar entry streaming handling and add in-memory gzip/tgz tests
- Fix tar entry handling: properly consume directory entries (resume stream) and wait for entry end before continuing to next header
- Wrap tar file entries with a PassThrough so extracted StreamFile instances can be consumed while the tar extractor continues
- Handle nested archives correctly by piping resultStream -> decompressionStream -> analyzer -> unpacker, avoiding premature end signals
- Add and expand tests in test/test.gzip.ts: verify package.json and TS/license files after extraction, add in-memory gzip extraction test, and add real tgz-in-memory download+extraction test
- Minor logging improvements for tar extraction flow
## 2025-08-18 - 4.2.1 - fix(gzip)
Improve gzip streaming decompression, archive analysis and unpacking; add gzip tests
- Add a streaming DecompressGunzipTransform using fflate.Gunzip with proper _flush handling to support chunked gzip input and avoid buffering issues.
- Refactor ArchiveAnalyzer: introduce IAnalyzedResult, getAnalyzedStream(), and getDecompressionStream() to better detect mime types and wire appropriate decompression streams (gzip, zip, bzip2, tar).
- Use SmartRequest response streams converted via stream.Readable.fromWeb for URL sources in SmartArchive.getArchiveStream() to improve remote archive handling.
- Improve nested archive unpacking and SmartArchive export pipeline: more robust tar/zip handling, consistent SmartDuplex usage and backpressure handling.
- Enhance exportToFs: ensure directories, improved logging for relative paths, and safer write-stream wiring.
- Add comprehensive gzip-focused tests (test/test.gzip.ts) covering file extraction, stream extraction, header filename handling, large files, and a real-world tgz-from-URL extraction scenario.
## 2025-08-18 - 4.2.0 - feat(classes.smartarchive)
Support URL streams, recursive archive unpacking and filesystem export; improve ZIP/GZIP/BZIP2 robustness; CI and package metadata updates
- Add exportToFs(targetDir, fileName?) to write extracted StreamFile objects to the filesystem (ensures directories, logs relative paths, waits for write completion).
- Implement exportToStreamOfStreamFiles with recursive unpacking pipeline that handles application/x-tar (tar-stream Extract), application/zip (fflate Unzip), nested archives and StreamIntake for StreamFile results.
- Enhance getArchiveStream() to support URL/web streams (SmartRequest) and return Node Readable streams for remote archives.
- Make ZIP decompression more robust: accept ArrayBuffer-like chunks, coerce to Buffer before pushing to fflate.Unzip, and ensure SmartDuplex handling of results.
- Fixes and improvements to bzip2/gzip/tar tool implementations (various bug/formatting fixes, safer CRC and stream handling).
- Update CI workflows to use new registry image and adjust npmci install path; minor .gitignore additions.
- Package metadata tweaks: bugs URL and homepage updated, packageManager/pnpm fields adjusted.
- Documentation/readme expanded and polished with quick start, examples and API reference updates.
- Small test and plugin export cleanups (formatting and trailing commas removed/added).
- TypeScript/formatting fixes across many files (consistent casing, trailing commas, typings, tsconfig additions).
## 2025-08-18 - 4.1.0 - feat(classes.smartarchive)
Support URL web streams, add recursive archive unpacking and filesystem export, and improve ZIP decompression robustness
- ts/classes.smartarchive.ts: add exportToFs(targetDir, fileName?) to write extracted StreamFile objects to the filesystem (ensures directories, logs relative paths, waits for write completion).
- ts/classes.smartarchive.ts: implement exportToStreamOfStreamFiles with recursive unpacking pipeline that handles application/x-tar (tar-stream Extract), application/zip (fflate unzip), nested archives and StreamIntake for StreamFile results.
- ts/classes.smartarchive.ts: improve getArchiveStream() for URL sources by using SmartRequest.create().url(...).get() and converting the returned Web stream into a Node Readable stream.
- ts/classes.ziptools.ts: make ZIP decompression writeFunction more robust — accept non-Buffer chunks, coerce to Buffer before pushing to fflate.Unzip, and loosen the writeFunction typing to handle incoming ArrayBuffer-like data.
## 2024-10-13 - 4.0.39 - fix(core)
Fix dependencies and update documentation.
- Ensure package uses the latest dependencies
- Reviewed and grouped imports in TypeScript files
- Updated readme with advanced usage examples
## 2024-10-13 - 4.0.38 - fix(dependencies)
Update dependencies to latest versions
- Updated @push.rocks/smartfile to version 11.0.21
- Updated @push.rocks/smartpromise to version 4.0.4
- Updated @push.rocks/smartstream to version 3.0.46
- Updated @push.rocks/smarturl to version 3.1.0
- Updated file-type to version 19.5.0
- Updated @git.zone/tsbuild to version 2.1.84
- Updated @git.zone/tsrun to version 1.2.49
- Updated @push.rocks/tapbundle to version 5.3.0
## 2024-06-08 - 4.0.24 to 4.0.37 - Fixes and Updates
Core updates and bug fixes were implemented in versions 4.0.24 through 4.0.37.
- Repeated core updates and fixes applied consistently across multiple versions.
## 2024-06-06 - 4.0.22 to 4.0.23 - Descriptions and Fixes Updates
Efforts to update documentation and core features.
- "update description" in 4.0.22
- Updates to `tsconfig` and `npmextra.json` were performed.
- Ongoing core fixes.
## 2023-11-06 - 4.0.0 - Major Update with Breaking Changes
Introduction of significant updates and breaking changes.
- Transition to new version 4.0.0 with core updates.
- Break in compatibility due to major structural changes with core functionalities.
## 2023-07-11 - 3.0.6 - Organizational Changes
Structural reorganization and updates to the organization schema.
- Switch to new organizational schema implemented.
## 2022-04-04 - 3.0.0 - Build Updates and Breaking Changes
Major build update introducing breaking changes.
- Introduction of ESM structure with breaking changes.
## 2016-01-18 - 0.0.0 to 1.0.0 - Initial Development and Launch
Initial software development and establishment of core features.
- Project set-up including Travis CI integration.
- Launch of the first full version with code restructuring.
- Added callback support.

6945
deno.lock generated Normal file

File diff suppressed because it is too large Load Diff

7
dist_ts/index.d.ts vendored
View File

@@ -1 +1,8 @@
export * from './interfaces.js';
export * from './errors.js';
export * from './classes.smartarchive.js'; export * from './classes.smartarchive.js';
export * from './classes.tartools.js';
export * from './classes.ziptools.js';
export * from './classes.gziptools.js';
export * from './classes.bzip2tools.js';
export * from './classes.archiveanalyzer.js';

View File

@@ -1,2 +1,13 @@
// Core types and errors
export * from './interfaces.js';
export * from './errors.js';
// Main archive class
export * from './classes.smartarchive.js'; export * from './classes.smartarchive.js';
//# sourceMappingURL=data:application/json;base64,eyJ2ZXJzaW9uIjozLCJmaWxlIjoiaW5kZXguanMiLCJzb3VyY2VSb290IjoiIiwic291cmNlcyI6WyIuLi90cy9pbmRleC50cyJdLCJuYW1lcyI6W10sIm1hcHBpbmdzIjoiQUFBQSxjQUFjLDJCQUEyQixDQUFDIn0= // Format-specific tools
export * from './classes.tartools.js';
export * from './classes.ziptools.js';
export * from './classes.gziptools.js';
export * from './classes.bzip2tools.js';
// Archive analysis
export * from './classes.archiveanalyzer.js';
//# sourceMappingURL=data:application/json;base64,eyJ2ZXJzaW9uIjozLCJmaWxlIjoiaW5kZXguanMiLCJzb3VyY2VSb290IjoiIiwic291cmNlcyI6WyIuLi90cy9pbmRleC50cyJdLCJuYW1lcyI6W10sIm1hcHBpbmdzIjoiQUFBQSx3QkFBd0I7QUFDeEIsY0FBYyxpQkFBaUIsQ0FBQztBQUNoQyxjQUFjLGFBQWEsQ0FBQztBQUU1QixxQkFBcUI7QUFDckIsY0FBYywyQkFBMkIsQ0FBQztBQUUxQyx3QkFBd0I7QUFDeEIsY0FBYyx1QkFBdUIsQ0FBQztBQUN0QyxjQUFjLHVCQUF1QixDQUFDO0FBQ3RDLGNBQWMsd0JBQXdCLENBQUM7QUFDdkMsY0FBYyx5QkFBeUIsQ0FBQztBQUV4QyxtQkFBbUI7QUFDbkIsY0FBYyw4QkFBOEIsQ0FBQyJ9

View File

@@ -6,12 +6,28 @@
"gitzone": { "gitzone": {
"projectType": "npm", "projectType": "npm",
"module": { "module": {
"githost": "gitlab.com", "githost": "code.foss.global",
"gitscope": "push.rocks", "gitscope": "push.rocks",
"gitrepo": "smartarchive", "gitrepo": "smartarchive",
"description": "work with archives", "description": "A library for working with archive files, providing utilities for compressing and decompressing data.",
"npmPackagename": "@push.rocks/smartarchive", "npmPackagename": "@push.rocks/smartarchive",
"license": "MIT" "license": "MIT",
"keywords": [
"archive",
"compression",
"decompression",
"zip",
"tar",
"gzip",
"bzip2",
"file extraction",
"file creation",
"data analysis",
"file stream"
]
} }
},
"tsdoc": {
"legal": "\n## License and Legal Information\n\nThis repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository. \n\n**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.\n\n### Trademarks\n\nThis project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.\n\n### Company Information\n\nTask Venture Capital GmbH \nRegistered at District court Bremen HRB 35230 HB, Germany\n\nFor any legal inquiries or if you require further information, please contact us via email at hello@task.vc.\n\nBy using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.\n"
} }
} }

View File

@@ -1,45 +1,44 @@
{ {
"name": "@push.rocks/smartarchive", "name": "@push.rocks/smartarchive",
"version": "4.0.14", "version": "5.0.0",
"description": "work with archives", "description": "A library for working with archive files, providing utilities for compressing and decompressing data.",
"main": "dist_ts/index.js", "main": "dist_ts/index.js",
"typings": "dist_ts/index.d.ts", "typings": "dist_ts/index.d.ts",
"type": "module", "type": "module",
"scripts": { "scripts": {
"test": "(tstest test/ --web)", "test": "(tstest test/ --verbose)",
"build": "tsbuild --web --allowimplicitany", "build": "tsbuild --web --allowimplicitany",
"buildDocs": "tsdoc" "buildDocs": "tsdoc"
}, },
"repository": { "repository": {
"type": "git", "type": "git",
"url": "git+https://github.com/pushrocks/smartarchive.git" "url": "https://code.foss.global/push.rocks/smartarchive.git"
}, },
"author": "Lossless GmbH", "author": "Lossless GmbH",
"license": "MIT", "license": "MIT",
"bugs": { "bugs": {
"url": "https://github.com/pushrocks/smartarchive/issues" "url": "https://code.foss.global/push.rocks/smartarchive/issues"
}, },
"homepage": "https://github.com/pushrocks/smartarchive#readme", "homepage": "https://code.foss.global/push.rocks/smartarchive#readme",
"dependencies": { "dependencies": {
"@push.rocks/smartfile": "^11.0.0", "@push.rocks/smartdelay": "^3.0.5",
"@push.rocks/smartpath": "^5.0.11", "@push.rocks/smartfile": "^13.0.0",
"@push.rocks/smartpromise": "^4.0.3", "@push.rocks/smartpath": "^6.0.0",
"@push.rocks/smartrequest": "^2.0.21", "@push.rocks/smartpromise": "^4.2.3",
"@push.rocks/smartrx": "^3.0.7", "@push.rocks/smartrequest": "^4.2.2",
"@push.rocks/smartstream": "^3.0.26", "@push.rocks/smartrx": "^3.0.10",
"@push.rocks/smartunique": "^3.0.6", "@push.rocks/smartstream": "^3.2.5",
"@push.rocks/smarturl": "^3.0.7", "@push.rocks/smartunique": "^3.0.9",
"@types/tar-stream": "^3.1.3", "@push.rocks/smarturl": "^3.1.0",
"fflate": "^0.8.1", "@types/tar-stream": "^3.1.4",
"file-type": "^18.7.0", "fflate": "^0.8.2",
"tar-stream": "^3.1.6", "file-type": "^21.0.0",
"through": "^2.3.8" "tar-stream": "^3.1.7"
}, },
"devDependencies": { "devDependencies": {
"@git.zone/tsbuild": "^2.1.66", "@git.zone/tsbuild": "^3.1.0",
"@git.zone/tsrun": "^1.2.44", "@git.zone/tsrun": "^2.0.0",
"@git.zone/tstest": "^1.0.84", "@git.zone/tstest": "^3.1.3"
"@push.rocks/tapbundle": "^5.0.15"
}, },
"private": false, "private": false,
"files": [ "files": [
@@ -56,5 +55,22 @@
], ],
"browserslist": [ "browserslist": [
"last 1 chrome versions" "last 1 chrome versions"
] ],
"keywords": [
"archive",
"compression",
"decompression",
"zip",
"tar",
"gzip",
"bzip2",
"file extraction",
"file creation",
"data analysis",
"file stream"
],
"packageManager": "pnpm@10.14.0+sha512.ad27a79641b49c3e481a16a805baa71817a04bbe06a38d17e60e2eaee83f6a146c6a688125f5792e48dd5ba30e7da52a5cda4c3992b9ccf333f9ce223af84748",
"pnpm": {
"overrides": {}
}
} }

13308
pnpm-lock.yaml generated

File diff suppressed because it is too large Load Diff

4
pnpm-workspace.yaml Normal file
View File

@@ -0,0 +1,4 @@
onlyBuiltDependencies:
- esbuild
- mongodb-memory-server
- puppeteer

38
readme.hints.md Normal file
View File

@@ -0,0 +1,38 @@
# Smartarchive Development Hints
## Dependency Upgrades (2025-01-25)
### Completed Upgrades
- **@git.zone/tsbuild**: ^2.6.6 → ^3.1.0
- **@git.zone/tsrun**: ^1.3.3 → ^2.0.0
- **@git.zone/tstest**: ^2.3.4 → ^3.1.3
- **@push.rocks/smartfile**: ^11.2.7 → ^13.0.0
### Migration Notes
#### Smartfile v13 Migration
Smartfile v13 removed filesystem operations (`fs`, `memory`, `fsStream` namespaces). These were replaced with Node.js native `fs` and `fs/promises`:
**Replacements made:**
- `smartfile.fs.ensureDir(path)``fsPromises.mkdir(path, { recursive: true })`
- `smartfile.fs.stat(path)``fsPromises.stat(path)`
- `smartfile.fs.toReadStream(path)``fs.createReadStream(path)`
- `smartfile.fs.toStringSync(path)``fsPromises.readFile(path, 'utf8')`
- `smartfile.fs.listFileTree(dir, pattern)` → custom `listFileTree()` helper
- `smartfile.fsStream.createReadStream(path)``fs.createReadStream(path)`
- `smartfile.fsStream.createWriteStream(path)``fs.createWriteStream(path)`
- `smartfile.memory.toFs(content, path)``fsPromises.writeFile(path, content)`
**Still using from smartfile v13:**
- `SmartFile` class (in-memory file representation)
- `StreamFile` class (streaming file handling)
### Removed Dependencies
- `through@2.3.8` - was unused in the codebase
## Architecture Notes
- Uses `fflate` for ZIP/GZIP compression (pure JS, works in browser)
- Uses `tar-stream` for TAR archive handling
- Uses `file-type` for MIME type detection
- Custom BZIP2 implementation in `ts/bzip2/` directory

486
readme.md
View File

@@ -1,54 +1,460 @@
# @push.rocks/smartarchive # @push.rocks/smartarchive 📦
work with archives
## Availabililty and Links Powerful archive manipulation for modern Node.js applications.
* [npmjs.org (npm package)](https://www.npmjs.com/package/@push.rocks/smartarchive)
* [gitlab.com (source)](https://gitlab.com/push.rocks/smartarchive)
* [github.com (source mirror)](https://github.com/push.rocks/smartarchive)
* [docs (typedoc)](https://push.rocks.gitlab.io/smartarchive/)
## Status for master `@push.rocks/smartarchive` is a versatile library for handling archive files with a focus on developer experience. Work with **zip**, **tar**, **gzip**, and **bzip2** formats through a unified, streaming-optimized API.
Status Category | Status Badge ## Issue Reporting and Security
-- | --
GitLab Pipelines | [![pipeline status](https://gitlab.com/push.rocks/smartarchive/badges/master/pipeline.svg)](https://lossless.cloud)
GitLab Pipline Test Coverage | [![coverage report](https://gitlab.com/push.rocks/smartarchive/badges/master/coverage.svg)](https://lossless.cloud)
npm | [![npm downloads per month](https://badgen.net/npm/dy/@push.rocks/smartarchive)](https://lossless.cloud)
Snyk | [![Known Vulnerabilities](https://badgen.net/snyk/push.rocks/smartarchive)](https://lossless.cloud)
TypeScript Support | [![TypeScript](https://badgen.net/badge/TypeScript/>=%203.x/blue?icon=typescript)](https://lossless.cloud)
node Support | [![node](https://img.shields.io/badge/node->=%2010.x.x-blue.svg)](https://nodejs.org/dist/latest-v10.x/docs/api/)
Code Style | [![Code Style](https://badgen.net/badge/style/prettier/purple)](https://lossless.cloud)
PackagePhobia (total standalone install weight) | [![PackagePhobia](https://badgen.net/packagephobia/install/@push.rocks/smartarchive)](https://lossless.cloud)
PackagePhobia (package size on registry) | [![PackagePhobia](https://badgen.net/packagephobia/publish/@push.rocks/smartarchive)](https://lossless.cloud)
BundlePhobia (total size when bundled) | [![BundlePhobia](https://badgen.net/bundlephobia/minzip/@push.rocks/smartarchive)](https://lossless.cloud)
## Usage For reporting bugs, issues, or security vulnerabilities, please visit [community.foss.global/](https://community.foss.global/). This is the central community hub for all issue reporting. Developers who sign and comply with our contribution agreement and go through identification can also get a [code.foss.global/](https://code.foss.global/) account to submit Pull Requests directly.
Use TypeScript for best in class instellisense. ## Features 🚀
```javascript - 📁 **Multi-format support** Handle `.zip`, `.tar`, `.tar.gz`, `.tgz`, and `.bz2` archives
import * as smartarchive from 'smartarchive'; - 🌊 **Streaming-first architecture** Process large archives without memory constraints
smartarchive - 🔄 **Unified API** Consistent interface across different archive formats
.get({ - 🎯 **Smart detection** Automatically identifies archive types via magic bytes
from: 'https://example.com/example.zip', -**High performance** Built on `tar-stream` and `fflate` for speed
toPath: '/some/local/absolute/path', - 🔧 **Flexible I/O** Work with files, URLs, and streams seamlessly
}) - 🛠️ **Modern TypeScript** Full type safety and excellent IDE support
.then(/*...*/);
## Installation 📥
```bash
# Using pnpm (recommended)
pnpm add @push.rocks/smartarchive
# Using npm
npm install @push.rocks/smartarchive
# Using yarn
yarn add @push.rocks/smartarchive
``` ```
For further information read the linked docs at the top of this README. ## Quick Start 🎯
> MIT licensed | **©** [Lossless GmbH](https://lossless.gmbh) ### Extract an archive from URL
> | By using this npm module you agree to our [privacy policy](https://lossless.gmbH/privacy.html)
[![repo-footer](https://pushrocks.gitlab.io/assets/repo-footer.svg)](https://push.rocks) ```typescript
import { SmartArchive } from '@push.rocks/smartarchive';
## Contribution // Extract a .tar.gz archive from a URL directly to the filesystem
const archive = await SmartArchive.fromArchiveUrl(
'https://registry.npmjs.org/some-package/-/some-package-1.0.0.tgz'
);
await archive.exportToFs('./extracted');
```
We are always happy for code contributions. If you are not the code contributing type that is ok. Still, maintaining Open Source repositories takes considerable time and thought. If you like the quality of what we do and our modules are useful to you we would appreciate a little monthly contribution: You can [contribute one time](https://lossless.link/contribute-onetime) or [contribute monthly](https://lossless.link/contribute). :) ### Process archive as a stream
For further information read the linked docs at the top of this readme. ```typescript
import { SmartArchive } from '@push.rocks/smartarchive';
## Legal // Stream-based processing for memory efficiency
> MIT licensed | **©** [Task Venture Capital GmbH](https://task.vc) const archive = await SmartArchive.fromArchiveFile('./large-archive.zip');
| By using this npm module you agree to our [privacy policy](https://lossless.gmbH/privacy) const streamOfFiles = await archive.exportToStreamOfStreamFiles();
// Process each file in the archive
streamOfFiles.on('data', async (streamFile) => {
console.log(`Processing ${streamFile.relativeFilePath}`);
const readStream = await streamFile.createReadStream();
// Handle individual file stream
});
streamOfFiles.on('end', () => {
console.log('Extraction complete');
});
```
## Core Concepts 💡
### Archive Sources
`SmartArchive` accepts archives from three sources:
| Source | Method | Use Case |
|--------|--------|----------|
| **URL** | `SmartArchive.fromArchiveUrl(url)` | Download and process archives from the web |
| **File** | `SmartArchive.fromArchiveFile(path)` | Load archives from the local filesystem |
| **Stream** | `SmartArchive.fromArchiveStream(stream)` | Process archives from any Node.js stream |
### Export Destinations
| Destination | Method | Use Case |
|-------------|--------|----------|
| **Filesystem** | `exportToFs(targetDir, fileName?)` | Extract directly to a directory |
| **Stream of files** | `exportToStreamOfStreamFiles()` | Process files individually as `StreamFile` objects |
## Usage Examples 🔨
### Working with ZIP files
```typescript
import { SmartArchive } from '@push.rocks/smartarchive';
// Extract a ZIP file
const zipArchive = await SmartArchive.fromArchiveFile('./archive.zip');
await zipArchive.exportToFs('./output');
// Stream ZIP contents for processing
const fileStream = await zipArchive.exportToStreamOfStreamFiles();
fileStream.on('data', async (streamFile) => {
if (streamFile.relativeFilePath.endsWith('.json')) {
const readStream = await streamFile.createReadStream();
// Process JSON files from the archive
}
});
```
### Working with TAR archives
```typescript
import { SmartArchive, TarTools } from '@push.rocks/smartarchive';
// Extract a .tar.gz file
const tarGzArchive = await SmartArchive.fromArchiveFile('./archive.tar.gz');
await tarGzArchive.exportToFs('./extracted');
// Create a TAR archive using TarTools directly
const tarTools = new TarTools();
const pack = await tarTools.getPackStream();
// Add files to the pack
await tarTools.addFileToPack(pack, {
fileName: 'hello.txt',
content: 'Hello, World!'
});
await tarTools.addFileToPack(pack, {
fileName: 'data.json',
content: Buffer.from(JSON.stringify({ foo: 'bar' }))
});
// Finalize and pipe to destination
pack.finalize();
pack.pipe(createWriteStream('./output.tar'));
```
### Pack a directory into TAR
```typescript
import { TarTools } from '@push.rocks/smartarchive';
import { createWriteStream } from 'fs';
const tarTools = new TarTools();
// Pack an entire directory
const pack = await tarTools.packDirectory('./src');
pack.finalize();
pack.pipe(createWriteStream('./source.tar'));
```
### Extracting from URLs
```typescript
import { SmartArchive } from '@push.rocks/smartarchive';
// Download and extract npm packages
const npmPackage = await SmartArchive.fromArchiveUrl(
'https://registry.npmjs.org/@push.rocks/smartfile/-/smartfile-11.2.7.tgz'
);
await npmPackage.exportToFs('./node_modules/@push.rocks/smartfile');
// Or process as stream for memory efficiency
const stream = await npmPackage.exportToStreamOfStreamFiles();
stream.on('data', async (file) => {
console.log(`Extracted: ${file.relativeFilePath}`);
});
```
### Working with GZIP files
```typescript
import { SmartArchive, GzipTools } from '@push.rocks/smartarchive';
import { createReadStream, createWriteStream } from 'fs';
// Decompress a .gz file - provide filename since gzip doesn't store it
const gzipArchive = await SmartArchive.fromArchiveFile('./data.json.gz');
await gzipArchive.exportToFs('./decompressed', 'data.json');
// Use GzipTools directly for streaming decompression
const gzipTools = new GzipTools();
const decompressStream = gzipTools.getDecompressionStream();
createReadStream('./compressed.gz')
.pipe(decompressStream)
.pipe(createWriteStream('./decompressed.txt'));
```
### Working with BZIP2 files
```typescript
import { SmartArchive } from '@push.rocks/smartarchive';
// Handle .bz2 files
const bzipArchive = await SmartArchive.fromArchiveUrl(
'https://example.com/data.bz2'
);
await bzipArchive.exportToFs('./extracted', 'data.txt');
```
### In-memory processing (no filesystem)
```typescript
import { SmartArchive } from '@push.rocks/smartarchive';
import { Readable } from 'stream';
// Process archives entirely in memory
const compressedBuffer = await fetchCompressedData();
const memoryStream = Readable.from(compressedBuffer);
const archive = await SmartArchive.fromArchiveStream(memoryStream);
const streamFiles = await archive.exportToStreamOfStreamFiles();
const extractedFiles: Array<{ name: string; content: Buffer }> = [];
streamFiles.on('data', async (streamFile) => {
const chunks: Buffer[] = [];
const readStream = await streamFile.createReadStream();
for await (const chunk of readStream) {
chunks.push(chunk);
}
extractedFiles.push({
name: streamFile.relativeFilePath,
content: Buffer.concat(chunks)
});
});
await new Promise((resolve) => streamFiles.on('end', resolve));
console.log(`Extracted ${extractedFiles.length} files in memory`);
```
### Nested archive handling (e.g., .tar.gz)
The library automatically handles nested compression. A `.tar.gz` file is:
1. First decompressed from gzip
2. Then unpacked from tar
This happens transparently:
```typescript
import { SmartArchive } from '@push.rocks/smartarchive';
// Automatically handles gzip → tar extraction chain
const tgzArchive = await SmartArchive.fromArchiveFile('./package.tar.gz');
await tgzArchive.exportToFs('./extracted');
```
## API Reference 📚
### SmartArchive Class
The main entry point for archive operations.
#### Static Factory Methods
```typescript
// Create from URL - downloads and processes archive
SmartArchive.fromArchiveUrl(url: string): Promise<SmartArchive>
// Create from local file path
SmartArchive.fromArchiveFile(path: string): Promise<SmartArchive>
// Create from any Node.js readable stream
SmartArchive.fromArchiveStream(stream: Readable | Duplex | Transform): Promise<SmartArchive>
```
#### Instance Methods
```typescript
// Extract all files to a directory
// fileName is optional - used for single-file archives (like .gz) that don't store filename
exportToFs(targetDir: string, fileName?: string): Promise<void>
// Get a stream that emits StreamFile objects for each file in the archive
exportToStreamOfStreamFiles(): Promise<StreamIntake<StreamFile>>
// Get the raw archive stream (useful for piping)
getArchiveStream(): Promise<Readable>
```
#### Instance Properties
```typescript
archive.tarTools // TarTools instance for TAR-specific operations
archive.zipTools // ZipTools instance for ZIP-specific operations
archive.gzipTools // GzipTools instance for GZIP-specific operations
archive.bzip2Tools // Bzip2Tools instance for BZIP2-specific operations
archive.archiveAnalyzer // ArchiveAnalyzer for inspecting archive type
```
### TarTools Class
TAR-specific operations for creating and extracting TAR archives.
```typescript
import { TarTools } from '@push.rocks/smartarchive';
const tarTools = new TarTools();
// Get a tar pack stream for creating archives
const pack = await tarTools.getPackStream();
// Add files to a pack stream
await tarTools.addFileToPack(pack, {
fileName: 'file.txt', // Name in archive
content: 'Hello World', // String, Buffer, Readable, SmartFile, or StreamFile
byteLength?: number, // Optional: specify size for streams
filePath?: string // Optional: path to file on disk
});
// Pack an entire directory
const pack = await tarTools.packDirectory('./src');
// Get extraction stream
const extract = tarTools.getDecompressionStream();
```
### ZipTools Class
ZIP-specific operations.
```typescript
import { ZipTools } from '@push.rocks/smartarchive';
const zipTools = new ZipTools();
// Get compression stream (for creating ZIP)
const compressor = zipTools.getCompressionStream();
// Get decompression stream (for extracting ZIP)
const decompressor = zipTools.getDecompressionStream();
```
### GzipTools Class
GZIP compression/decompression streams.
```typescript
import { GzipTools } from '@push.rocks/smartarchive';
const gzipTools = new GzipTools();
// Get compression stream
const compressor = gzipTools.getCompressionStream();
// Get decompression stream
const decompressor = gzipTools.getDecompressionStream();
```
## Supported Formats 📋
| Format | Extension(s) | Extract | Create |
|--------|--------------|---------|--------|
| TAR | `.tar` | ✅ | ✅ |
| TAR.GZ / TGZ | `.tar.gz`, `.tgz` | ✅ | ⚠️ |
| ZIP | `.zip` | ✅ | ⚠️ |
| GZIP | `.gz` | ✅ | ✅ |
| BZIP2 | `.bz2` | ✅ | ❌ |
✅ Full support | ⚠️ Partial/basic support | ❌ Not supported
## Performance Tips 🏎️
1. **Use streaming for large files** Avoid loading entire archives into memory with `exportToStreamOfStreamFiles()`
2. **Provide byte lengths when known** When adding streams to TAR, provide `byteLength` for better performance
3. **Process files as they stream** Don't collect all files into an array unless necessary
4. **Choose the right format** TAR.GZ for Unix/compression, ZIP for cross-platform compatibility
## Error Handling 🛡️
```typescript
import { SmartArchive } from '@push.rocks/smartarchive';
try {
const archive = await SmartArchive.fromArchiveUrl('https://example.com/file.zip');
await archive.exportToFs('./output');
} catch (error) {
if (error.code === 'ENOENT') {
console.error('Archive file not found');
} else if (error.code === 'EACCES') {
console.error('Permission denied');
} else if (error.message.includes('fetch')) {
console.error('Network error downloading archive');
} else {
console.error('Archive extraction failed:', error.message);
}
}
```
## Real-World Use Cases 🌍
### CI/CD: Download & Extract Build Artifacts
```typescript
const artifacts = await SmartArchive.fromArchiveUrl(
`${CI_SERVER}/artifacts/build-${BUILD_ID}.zip`
);
await artifacts.exportToFs('./dist');
```
### Backup System: Restore from Archive
```typescript
const backup = await SmartArchive.fromArchiveFile('./backup-2024.tar.gz');
await backup.exportToFs('/restore/location');
```
### NPM Package Inspection
```typescript
const pkg = await SmartArchive.fromArchiveUrl(
'https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz'
);
const files = await pkg.exportToStreamOfStreamFiles();
files.on('data', async (file) => {
if (file.relativeFilePath.includes('package.json')) {
const stream = await file.createReadStream();
// Read and analyze package.json
}
});
```
### Data Pipeline: Process Compressed Datasets
```typescript
const dataset = await SmartArchive.fromArchiveUrl(
'https://data.source/dataset.tar.gz'
);
const files = await dataset.exportToStreamOfStreamFiles();
files.on('data', async (file) => {
if (file.relativeFilePath.endsWith('.csv')) {
const stream = await file.createReadStream();
// Stream CSV processing
}
});
```
## License and Legal Information
This repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository.
**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.
### Trademarks
This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.
### Company Information
Task Venture Capital GmbH
Registered at District court Bremen HRB 35230 HB, Germany
For any legal inquiries or if you require further information, please contact us via email at hello@task.vc.
By using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.

View File

@@ -1,13 +1,33 @@
import * as path from 'path'; import * as path from 'node:path';
import * as fs from 'node:fs';
import * as fsPromises from 'node:fs/promises';
import * as smartpath from '@push.rocks/smartpath'; import * as smartpath from '@push.rocks/smartpath';
import * as smartfile from '@push.rocks/smartfile'; import * as smartfile from '@push.rocks/smartfile';
import * as smartrequest from '@push.rocks/smartrequest'; import * as smartrequest from '@push.rocks/smartrequest';
import * as smartstream from '@push.rocks/smartstream'; import * as smartstream from '@push.rocks/smartstream';
export { export { path, fs, fsPromises, smartpath, smartfile, smartrequest, smartstream };
path,
smartpath, /**
smartfile, * List files in a directory recursively, returning relative paths
smartrequest, */
smartstream, export async function listFileTree(dirPath: string, _pattern: string = '**/*'): Promise<string[]> {
const results: string[] = [];
async function walkDir(currentPath: string, relativePath: string = '') {
const entries = await fsPromises.readdir(currentPath, { withFileTypes: true });
for (const entry of entries) {
const entryRelPath = relativePath ? path.join(relativePath, entry.name) : entry.name;
const entryFullPath = path.join(currentPath, entry.name);
if (entry.isDirectory()) {
await walkDir(entryFullPath, entryRelPath);
} else if (entry.isFile()) {
results.push(entryRelPath);
}
}
}
await walkDir(dirPath);
return results;
} }

401
test/test.gzip.node+deno.ts Normal file
View File

@@ -0,0 +1,401 @@
import { tap, expect } from '@git.zone/tstest/tapbundle';
import * as plugins from './plugins.js';
import * as smartarchive from '../ts/index.js';
const testPaths = {
nogitDir: plugins.path.join(
plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
'../.nogit/',
),
gzipTestDir: plugins.path.join(
plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
'../.nogit/gzip-test',
),
};
tap.preTask('should prepare test directories', async () => {
await plugins.fsPromises.mkdir(testPaths.gzipTestDir, { recursive: true });
});
tap.test('should create and extract a gzip file', async () => {
// Create test data
const testContent = 'This is a test file for gzip compression and decompression.\n'.repeat(100);
const testFileName = 'test-file.txt';
const gzipFileName = 'test-file.txt.gz';
// Write the original file
await plugins.fsPromises.writeFile(
plugins.path.join(testPaths.gzipTestDir, testFileName),
testContent
);
// Create gzip compressed version using fflate directly
const fflate = await import('fflate');
const compressed = fflate.gzipSync(Buffer.from(testContent));
await plugins.fsPromises.writeFile(
plugins.path.join(testPaths.gzipTestDir, gzipFileName),
Buffer.from(compressed)
);
// Now test extraction using SmartArchive
const gzipArchive = await smartarchive.SmartArchive.fromFile(
plugins.path.join(testPaths.gzipTestDir, gzipFileName)
);
// Export to a new location
const extractPath = plugins.path.join(testPaths.gzipTestDir, 'extracted');
await plugins.fsPromises.mkdir(extractPath, { recursive: true });
// Provide a filename since gzip doesn't contain filename metadata
await gzipArchive.extractToDirectory(extractPath, { fileName: 'test-file.txt' });
// Read the extracted file
const extractedContent = await plugins.fsPromises.readFile(
plugins.path.join(extractPath, 'test-file.txt'),
'utf8'
);
// Verify the content matches
expect(extractedContent).toEqual(testContent);
});
tap.test('should handle gzip stream extraction', async () => {
// Create test data
const testContent = 'Stream test data for gzip\n'.repeat(50);
const gzipFileName = 'stream-test.txt.gz';
// Create gzip compressed version
const fflate = await import('fflate');
const compressed = fflate.gzipSync(Buffer.from(testContent));
await plugins.fsPromises.writeFile(
plugins.path.join(testPaths.gzipTestDir, gzipFileName),
Buffer.from(compressed)
);
// Create a read stream for the gzip file
const gzipStream = plugins.fs.createReadStream(
plugins.path.join(testPaths.gzipTestDir, gzipFileName)
);
// Test extraction using SmartArchive from stream
const gzipArchive = await smartarchive.SmartArchive.fromStream(gzipStream);
// Export to stream and collect the result
const streamFiles: any[] = [];
const resultStream = await gzipArchive.extractToStream();
await new Promise<void>((resolve, reject) => {
resultStream.on('data', (streamFile) => {
streamFiles.push(streamFile);
});
resultStream.on('end', resolve);
resultStream.on('error', reject);
});
// Verify we got the expected file
expect(streamFiles.length).toBeGreaterThan(0);
// Read content from the stream file
if (streamFiles[0]) {
const chunks: Buffer[] = [];
const readStream = await streamFiles[0].createReadStream();
await new Promise<void>((resolve, reject) => {
readStream.on('data', (chunk: Buffer) => chunks.push(chunk));
readStream.on('end', resolve);
readStream.on('error', reject);
});
const extractedContent = Buffer.concat(chunks).toString();
expect(extractedContent).toEqual(testContent);
}
});
tap.test('should handle gzip files with original filename in header', async () => {
// Test with a real-world gzip file that includes filename in header
const testContent = 'File with name in gzip header\n'.repeat(30);
const originalFileName = 'original-name.log';
const gzipFileName = 'compressed.gz';
// Create a proper gzip with filename header using Node's zlib
const zlib = await import('node:zlib');
const gzipBuffer = await new Promise<Buffer>((resolve, reject) => {
zlib.gzip(Buffer.from(testContent), {
level: 9,
// Note: Node's zlib doesn't support embedding filename directly,
// but we can test the extraction anyway
}, (err, result) => {
if (err) reject(err);
else resolve(result);
});
});
await plugins.fsPromises.writeFile(
plugins.path.join(testPaths.gzipTestDir, gzipFileName),
gzipBuffer
);
// Test extraction
const gzipArchive = await smartarchive.SmartArchive.fromFile(
plugins.path.join(testPaths.gzipTestDir, gzipFileName)
);
const extractPath = plugins.path.join(testPaths.gzipTestDir, 'header-test');
await plugins.fsPromises.mkdir(extractPath, { recursive: true });
// Provide a filename since gzip doesn't reliably contain filename metadata
await gzipArchive.extractToDirectory(extractPath, { fileName: 'compressed.txt' });
// Check if file was extracted (name might be derived from archive name)
const files = await plugins.listFileTree(extractPath, '**/*');
expect(files.length).toBeGreaterThan(0);
// Read and verify content
const extractedFile = files[0];
const extractedContent = await plugins.fsPromises.readFile(
plugins.path.join(extractPath, extractedFile || 'compressed.txt'),
'utf8'
);
expect(extractedContent).toEqual(testContent);
});
tap.test('should handle large gzip files', async () => {
// Create a larger test file
const largeContent = 'x'.repeat(1024 * 1024); // 1MB of 'x' characters
const gzipFileName = 'large-file.txt.gz';
// Compress the large file
const fflate = await import('fflate');
const compressed = fflate.gzipSync(Buffer.from(largeContent));
await plugins.fsPromises.writeFile(
plugins.path.join(testPaths.gzipTestDir, gzipFileName),
Buffer.from(compressed)
);
// Test extraction
const gzipArchive = await smartarchive.SmartArchive.fromFile(
plugins.path.join(testPaths.gzipTestDir, gzipFileName)
);
const extractPath = plugins.path.join(testPaths.gzipTestDir, 'large-extracted');
await plugins.fsPromises.mkdir(extractPath, { recursive: true });
// Provide a filename since gzip doesn't contain filename metadata
await gzipArchive.extractToDirectory(extractPath, { fileName: 'large-file.txt' });
// Verify the extracted content
const files = await plugins.listFileTree(extractPath, '**/*');
expect(files.length).toBeGreaterThan(0);
const extractedContent = await plugins.fsPromises.readFile(
plugins.path.join(extractPath, files[0] || 'large-file.txt'),
'utf8'
);
expect(extractedContent.length).toEqual(largeContent.length);
expect(extractedContent).toEqual(largeContent);
});
tap.test('should handle real-world multi-chunk gzip from URL', async () => {
// Test with a real tgz file that will be processed in multiple chunks
const testUrl = 'https://registry.npmjs.org/@push.rocks/smartfile/-/smartfile-11.2.7.tgz';
// Download and extract the archive
const testArchive = await smartarchive.SmartArchive.fromUrl(testUrl);
const extractPath = plugins.path.join(testPaths.gzipTestDir, 'real-world-test');
await plugins.fsPromises.mkdir(extractPath, { recursive: true });
// This will test multi-chunk decompression as the file is larger
await testArchive.extractToDirectory(extractPath);
// Verify extraction worked
const files = await plugins.listFileTree(extractPath, '**/*');
expect(files.length).toBeGreaterThan(0);
// Check for expected package structure
const hasPackageJson = files.some(f => f.includes('package.json'));
expect(hasPackageJson).toBeTrue();
// Read and verify package.json content
const packageJsonPath = files.find(f => f.includes('package.json'));
if (packageJsonPath) {
const packageJsonContent = await plugins.fsPromises.readFile(
plugins.path.join(extractPath, packageJsonPath),
'utf8'
);
const packageJson = JSON.parse(packageJsonContent);
expect(packageJson.name).toEqual('@push.rocks/smartfile');
expect(packageJson.version).toEqual('11.2.7');
}
// Read and verify a TypeScript file
const tsFilePath = files.find(f => f.endsWith('.ts'));
if (tsFilePath) {
const tsFileContent = await plugins.fsPromises.readFile(
plugins.path.join(extractPath, tsFilePath),
'utf8'
);
// TypeScript files should have content
expect(tsFileContent.length).toBeGreaterThan(10);
console.log(` ✓ TypeScript file ${tsFilePath} has ${tsFileContent.length} bytes`);
}
// Read and verify license file
const licensePath = files.find(f => f.includes('license'));
if (licensePath) {
const licenseContent = await plugins.fsPromises.readFile(
plugins.path.join(extractPath, licensePath),
'utf8'
);
expect(licenseContent).toContain('MIT');
}
// Verify we can read multiple files without corruption
const readableFiles = files.filter(f =>
f.endsWith('.json') || f.endsWith('.md') || f.endsWith('.ts') || f.endsWith('.js')
).slice(0, 5); // Test first 5 readable files
for (const file of readableFiles) {
const content = await plugins.fsPromises.readFile(
plugins.path.join(extractPath, file),
'utf8'
);
expect(content).toBeDefined();
expect(content.length).toBeGreaterThan(0);
console.log(` ✓ Successfully read ${file} (${content.length} bytes)`);
}
});
tap.test('should handle gzip extraction fully in memory', async () => {
// Create test data in memory
const testContent = 'This is test data for in-memory gzip processing\n'.repeat(100);
// Compress using fflate in memory
const fflate = await import('fflate');
const compressed = fflate.gzipSync(Buffer.from(testContent));
// Create a stream from the compressed data
const { Readable } = await import('node:stream');
const compressedStream = Readable.from(Buffer.from(compressed));
// Process through SmartArchive without touching filesystem
const gzipArchive = await smartarchive.SmartArchive.fromStream(compressedStream);
// Export to stream of stream files (in memory)
const streamFiles: plugins.smartfile.StreamFile[] = [];
const resultStream = await gzipArchive.extractToStream();
await new Promise<void>((resolve, reject) => {
resultStream.on('data', (streamFile: plugins.smartfile.StreamFile) => {
streamFiles.push(streamFile);
});
resultStream.on('end', resolve);
resultStream.on('error', reject);
});
// Verify we got a file
expect(streamFiles.length).toBeGreaterThan(0);
// Read the content from memory without filesystem
const firstFile = streamFiles[0];
const chunks: Buffer[] = [];
const readStream = await firstFile.createReadStream();
await new Promise<void>((resolve, reject) => {
readStream.on('data', (chunk: Buffer) => chunks.push(chunk));
readStream.on('end', resolve);
readStream.on('error', reject);
});
const extractedContent = Buffer.concat(chunks).toString();
expect(extractedContent).toEqual(testContent);
console.log(` ✓ In-memory extraction successful (${extractedContent.length} bytes)`);
});
tap.test('should handle real tgz file fully in memory', async (tools) => {
await tools.timeout(10000); // Set 10 second timeout
// Download tgz file into memory
const response = await plugins.smartrequest.SmartRequest.create()
.url('https://registry.npmjs.org/@push.rocks/smartfile/-/smartfile-11.2.7.tgz')
.get();
const tgzBuffer = Buffer.from(await response.arrayBuffer());
console.log(` Downloaded ${tgzBuffer.length} bytes into memory`);
// Create stream from buffer
const { Readable: Readable2 } = await import('node:stream');
const tgzStream = Readable2.from(tgzBuffer);
// Process through SmartArchive in memory
const archive = await smartarchive.SmartArchive.fromStream(tgzStream);
// Export to stream of stream files (in memory)
const streamFiles: plugins.smartfile.StreamFile[] = [];
const resultStream = await archive.extractToStream();
await new Promise<void>((resolve, reject) => {
let timeout: NodeJS.Timeout;
const cleanup = () => {
clearTimeout(timeout);
};
timeout = setTimeout(() => {
cleanup();
resolve(); // Resolve after timeout if stream doesn't end
}, 5000);
resultStream.on('data', (streamFile: plugins.smartfile.StreamFile) => {
streamFiles.push(streamFile);
});
resultStream.on('end', () => {
cleanup();
resolve();
});
resultStream.on('error', (err) => {
cleanup();
reject(err);
});
});
console.log(` Extracted ${streamFiles.length} files in memory`);
// At minimum we should have extracted something
expect(streamFiles.length).toBeGreaterThan(0);
// Find and read package.json from memory
const packageJsonFile = streamFiles.find(f => f.relativeFilePath?.includes('package.json'));
if (packageJsonFile) {
const chunks: Buffer[] = [];
const readStream = await packageJsonFile.createReadStream();
await new Promise<void>((resolve, reject) => {
readStream.on('data', (chunk: Buffer) => chunks.push(chunk));
readStream.on('end', resolve);
readStream.on('error', reject);
});
const packageJsonContent = Buffer.concat(chunks).toString();
const packageJson = JSON.parse(packageJsonContent);
expect(packageJson.name).toEqual('@push.rocks/smartfile');
expect(packageJson.version).toEqual('11.2.7');
console.log(` ✓ Read package.json from memory: ${packageJson.name}@${packageJson.version}`);
}
// Read a few more files to verify integrity
const filesToCheck = streamFiles.slice(0, 3);
for (const file of filesToCheck) {
const chunks: Buffer[] = [];
const readStream = await file.createReadStream();
await new Promise<void>((resolve, reject) => {
readStream.on('data', (chunk: Buffer) => chunks.push(chunk));
readStream.on('end', resolve);
readStream.on('error', reject);
});
const content = Buffer.concat(chunks);
expect(content.length).toBeGreaterThan(0);
console.log(` ✓ Read ${file.relativeFilePath} from memory (${content.length} bytes)`);
}
});
export default tap.start();

51
test/test.node+deno.ts Normal file
View File

@@ -0,0 +1,51 @@
import { tap, expect } from '@git.zone/tstest/tapbundle';
import * as plugins from './plugins.js';
const testPaths = {
nogitDir: plugins.path.join(
plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
'../.nogit/',
),
remoteDir: plugins.path.join(
plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
'../.nogit/remote',
),
};
import * as smartarchive from '../ts/index.js';
tap.preTask('should prepare .nogit dir', async () => {
await plugins.fsPromises.mkdir(testPaths.remoteDir, { recursive: true });
});
tap.preTask('should prepare downloads', async (tools) => {
const response = await plugins.smartrequest.SmartRequest.create()
.url(
'https://verdaccio.lossless.digital/@pushrocks%2fwebsetup/-/websetup-2.0.14.tgz',
)
.get();
const downloadedFile: Buffer = Buffer.from(await response.arrayBuffer());
await plugins.fsPromises.writeFile(
plugins.path.join(testPaths.nogitDir, 'test.tgz'),
downloadedFile,
);
});
tap.test('should extract existing files on disk', async () => {
const testSmartarchive = await smartarchive.SmartArchive.fromUrl(
'https://verdaccio.lossless.digital/@pushrocks%2fwebsetup/-/websetup-2.0.14.tgz',
);
await testSmartarchive.extractToDirectory(testPaths.nogitDir);
});
tap.skip.test('should extract a b2zip', async () => {
const dataUrl =
'https://daten.offeneregister.de/de_companies_ocdata.jsonl.bz2';
const testArchive = await smartarchive.SmartArchive.fromUrl(dataUrl);
await testArchive.extractToDirectory(
plugins.path.join(testPaths.nogitDir, 'de_companies_ocdata.jsonl'),
);
});
await tap.start();

View File

@@ -1,50 +0,0 @@
import { tap, expect } from '@push.rocks/tapbundle';
import * as plugins from './plugins.js';
const testPaths = {
nogitDir: plugins.path.join(
plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
'../.nogit/'
),
remoteDir: plugins.path.join(
plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
'../.nogit/remote'
),
};
import * as smartarchive from '../ts/index.js';
tap.preTask('should prepare .nogit dir', async () => {
await plugins.smartfile.fs.ensureDir(testPaths.remoteDir);
});
tap.preTask('should prepare downloads', async (tools) => {
const downloadedFile: Buffer = (
await plugins.smartrequest.getBinary(
'https://verdaccio.lossless.digital/@pushrocks%2fwebsetup/-/websetup-2.0.14.tgz'
)
).body;
await plugins.smartfile.memory.toFs(
downloadedFile,
plugins.path.join(testPaths.nogitDir, 'test.tgz')
);
});
tap.test('should extract existing files on disk', async () => {
const testSmartarchive = await smartarchive.SmartArchive.fromArchiveUrl(
'https://verdaccio.lossless.digital/@pushrocks%2fwebsetup/-/websetup-2.0.14.tgz'
);
await testSmartarchive.exportToFs(testPaths.nogitDir);
});
tap.skip.test('should extract a b2zip', async () => {
const dataUrl = 'https://daten.offeneregister.de/de_companies_ocdata.jsonl.bz2';
const testArchive = await smartarchive.SmartArchive.fromArchiveUrl(dataUrl);
await testArchive.exportToFs(
plugins.path.join(testPaths.nogitDir, 'de_companies_ocdata.jsonl'),
'data.jsonl',
);
})
tap.start();

View File

@@ -1,8 +1,8 @@
/** /**
* autocreated commitinfo by @pushrocks/commitinfo * autocreated commitinfo by @push.rocks/commitinfo
*/ */
export const commitinfo = { export const commitinfo = {
name: '@push.rocks/smartarchive', name: '@push.rocks/smartarchive',
version: '4.0.14', version: '5.0.0',
description: 'work with archives' description: 'A library for working with archive files, providing utilities for compressing and decompressing data.'
} }

View File

@@ -1,41 +1,60 @@
var BITMASK = [0, 0x01, 0x03, 0x07, 0x0F, 0x1F, 0x3F, 0x7F, 0xFF]; import type { IBitReader } from '../interfaces.js';
// returns a function that reads bits. const BITMASK = [0, 0x01, 0x03, 0x07, 0x0f, 0x1f, 0x3f, 0x7f, 0xff] as const;
// takes a buffer iterator as input
export function bitIterator(nextBuffer: () => Buffer) { /**
var bit = 0, byte = 0; * Creates a bit reader function for BZIP2 decompression.
var bytes = nextBuffer(); * Takes a buffer iterator as input and returns a function that reads bits.
var f = function(n) { */
if (n === null && bit != 0) { // align to byte boundary export function bitIterator(nextBuffer: () => Buffer): IBitReader {
bit = 0 let bit = 0;
let byte = 0;
let bytes = nextBuffer();
let _bytesRead = 0;
const reader = function (n: number | null): number | void {
if (n === null && bit !== 0) {
// align to byte boundary
bit = 0;
byte++; byte++;
return; return;
} }
var result = 0;
while(n > 0) { let result = 0;
let remaining = n as number;
while (remaining > 0) {
if (byte >= bytes.length) { if (byte >= bytes.length) {
byte = 0; byte = 0;
bytes = nextBuffer(); bytes = nextBuffer();
} }
var left = 8 - bit;
if (bit === 0 && n > 0) const left = 8 - bit;
// @ts-ignore
f.bytesRead++; if (bit === 0 && remaining > 0) {
if (n >= left) { _bytesRead++;
}
if (remaining >= left) {
result <<= left; result <<= left;
result |= (BITMASK[left] & bytes[byte++]); result |= BITMASK[left] & bytes[byte++];
bit = 0; bit = 0;
n -= left; remaining -= left;
} else { } else {
result <<= n; result <<= remaining;
result |= ((bytes[byte] & (BITMASK[n] << (8 - n - bit))) >> (8 - n - bit)); result |= (bytes[byte] & (BITMASK[remaining] << (8 - remaining - bit))) >> (8 - remaining - bit);
bit += n; bit += remaining;
n = 0; remaining = 0;
} }
} }
return result; return result;
}; } as IBitReader;
// @ts-ignore
f.bytesRead = 0; Object.defineProperty(reader, 'bytesRead', {
return f; get: () => _bytesRead,
}; enumerable: true,
});
return reader;
}

View File

@@ -1,318 +1,427 @@
export class Bzip2Error extends Error { import { Bzip2Error, BZIP2_ERROR_CODES } from '../errors.js';
public name: string = 'Bzip2Error'; import type { IBitReader, IHuffmanGroup } from '../interfaces.js';
public message: string;
public stack = (new Error()).stack;
constructor(messageArg: string) { // Re-export Bzip2Error for backward compatibility
super(); export { Bzip2Error };
this.message = messageArg;
} /**
* Throw a BZIP2 error with proper error code
*/
function throwError(message: string, code: string = BZIP2_ERROR_CODES.INVALID_BLOCK_DATA): never {
throw new Bzip2Error(message, code);
} }
var messageArg = { /**
Error: function(message) {throw new Bzip2Error(message);} * BZIP2 decompression implementation
}; */
export class Bzip2 { export class Bzip2 {
public Bzip2Error = Bzip2Error; // CRC32 lookup table for BZIP2
public crcTable = public readonly crcTable: readonly number[] = [
[ 0x00000000, 0x04c11db7, 0x09823b6e, 0x0d4326d9, 0x130476dc, 0x17c56b6b,
0x00000000, 0x04c11db7, 0x09823b6e, 0x0d4326d9, 0x1a864db2, 0x1e475005, 0x2608edb8, 0x22c9f00f, 0x2f8ad6d6, 0x2b4bcb61,
0x130476dc, 0x17c56b6b, 0x1a864db2, 0x1e475005, 0x350c9b64, 0x31cd86d3, 0x3c8ea00a, 0x384fbdbd, 0x4c11db70, 0x48d0c6c7,
0x2608edb8, 0x22c9f00f, 0x2f8ad6d6, 0x2b4bcb61, 0x4593e01e, 0x4152fda9, 0x5f15adac, 0x5bd4b01b, 0x569796c2, 0x52568b75,
0x350c9b64, 0x31cd86d3, 0x3c8ea00a, 0x384fbdbd, 0x6a1936c8, 0x6ed82b7f, 0x639b0da6, 0x675a1011, 0x791d4014, 0x7ddc5da3,
0x4c11db70, 0x48d0c6c7, 0x4593e01e, 0x4152fda9, 0x709f7b7a, 0x745e66cd, 0x9823b6e0, 0x9ce2ab57, 0x91a18d8e, 0x95609039,
0x5f15adac, 0x5bd4b01b, 0x569796c2, 0x52568b75, 0x8b27c03c, 0x8fe6dd8b, 0x82a5fb52, 0x8664e6e5, 0xbe2b5b58, 0xbaea46ef,
0x6a1936c8, 0x6ed82b7f, 0x639b0da6, 0x675a1011, 0xb7a96036, 0xb3687d81, 0xad2f2d84, 0xa9ee3033, 0xa4ad16ea, 0xa06c0b5d,
0x791d4014, 0x7ddc5da3, 0x709f7b7a, 0x745e66cd, 0xd4326d90, 0xd0f37027, 0xddb056fe, 0xd9714b49, 0xc7361b4c, 0xc3f706fb,
0x9823b6e0, 0x9ce2ab57, 0x91a18d8e, 0x95609039, 0xceb42022, 0xca753d95, 0xf23a8028, 0xf6fb9d9f, 0xfbb8bb46, 0xff79a6f1,
0x8b27c03c, 0x8fe6dd8b, 0x82a5fb52, 0x8664e6e5, 0xe13ef6f4, 0xe5ffeb43, 0xe8bccd9a, 0xec7dd02d, 0x34867077, 0x30476dc0,
0xbe2b5b58, 0xbaea46ef, 0xb7a96036, 0xb3687d81, 0x3d044b19, 0x39c556ae, 0x278206ab, 0x23431b1c, 0x2e003dc5, 0x2ac12072,
0xad2f2d84, 0xa9ee3033, 0xa4ad16ea, 0xa06c0b5d, 0x128e9dcf, 0x164f8078, 0x1b0ca6a1, 0x1fcdbb16, 0x018aeb13, 0x054bf6a4,
0xd4326d90, 0xd0f37027, 0xddb056fe, 0xd9714b49, 0x0808d07d, 0x0cc9cdca, 0x7897ab07, 0x7c56b6b0, 0x71159069, 0x75d48dde,
0xc7361b4c, 0xc3f706fb, 0xceb42022, 0xca753d95, 0x6b93dddb, 0x6f52c06c, 0x6211e6b5, 0x66d0fb02, 0x5e9f46bf, 0x5a5e5b08,
0xf23a8028, 0xf6fb9d9f, 0xfbb8bb46, 0xff79a6f1, 0x571d7dd1, 0x53dc6066, 0x4d9b3063, 0x495a2dd4, 0x44190b0d, 0x40d816ba,
0xe13ef6f4, 0xe5ffeb43, 0xe8bccd9a, 0xec7dd02d, 0xaca5c697, 0xa864db20, 0xa527fdf9, 0xa1e6e04e, 0xbfa1b04b, 0xbb60adfc,
0x34867077, 0x30476dc0, 0x3d044b19, 0x39c556ae, 0xb6238b25, 0xb2e29692, 0x8aad2b2f, 0x8e6c3698, 0x832f1041, 0x87ee0df6,
0x278206ab, 0x23431b1c, 0x2e003dc5, 0x2ac12072, 0x99a95df3, 0x9d684044, 0x902b669d, 0x94ea7b2a, 0xe0b41de7, 0xe4750050,
0x128e9dcf, 0x164f8078, 0x1b0ca6a1, 0x1fcdbb16, 0xe9362689, 0xedf73b3e, 0xf3b06b3b, 0xf771768c, 0xfa325055, 0xfef34de2,
0x018aeb13, 0x054bf6a4, 0x0808d07d, 0x0cc9cdca, 0xc6bcf05f, 0xc27dede8, 0xcf3ecb31, 0xcbffd686, 0xd5b88683, 0xd1799b34,
0x7897ab07, 0x7c56b6b0, 0x71159069, 0x75d48dde, 0xdc3abded, 0xd8fba05a, 0x690ce0ee, 0x6dcdfd59, 0x608edb80, 0x644fc637,
0x6b93dddb, 0x6f52c06c, 0x6211e6b5, 0x66d0fb02, 0x7a089632, 0x7ec98b85, 0x738aad5c, 0x774bb0eb, 0x4f040d56, 0x4bc510e1,
0x5e9f46bf, 0x5a5e5b08, 0x571d7dd1, 0x53dc6066, 0x46863638, 0x42472b8f, 0x5c007b8a, 0x58c1663d, 0x558240e4, 0x51435d53,
0x4d9b3063, 0x495a2dd4, 0x44190b0d, 0x40d816ba, 0x251d3b9e, 0x21dc2629, 0x2c9f00f0, 0x285e1d47, 0x36194d42, 0x32d850f5,
0xaca5c697, 0xa864db20, 0xa527fdf9, 0xa1e6e04e, 0x3f9b762c, 0x3b5a6b9b, 0x0315d626, 0x07d4cb91, 0x0a97ed48, 0x0e56f0ff,
0xbfa1b04b, 0xbb60adfc, 0xb6238b25, 0xb2e29692, 0x1011a0fa, 0x14d0bd4d, 0x19939b94, 0x1d528623, 0xf12f560e, 0xf5ee4bb9,
0x8aad2b2f, 0x8e6c3698, 0x832f1041, 0x87ee0df6, 0xf8ad6d60, 0xfc6c70d7, 0xe22b20d2, 0xe6ea3d65, 0xeba91bbc, 0xef68060b,
0x99a95df3, 0x9d684044, 0x902b669d, 0x94ea7b2a, 0xd727bbb6, 0xd3e6a601, 0xdea580d8, 0xda649d6f, 0xc423cd6a, 0xc0e2d0dd,
0xe0b41de7, 0xe4750050, 0xe9362689, 0xedf73b3e, 0xcda1f604, 0xc960ebb3, 0xbd3e8d7e, 0xb9ff90c9, 0xb4bcb610, 0xb07daba7,
0xf3b06b3b, 0xf771768c, 0xfa325055, 0xfef34de2, 0xae3afba2, 0xaafbe615, 0xa7b8c0cc, 0xa379dd7b, 0x9b3660c6, 0x9ff77d71,
0xc6bcf05f, 0xc27dede8, 0xcf3ecb31, 0xcbffd686, 0x92b45ba8, 0x9675461f, 0x8832161a, 0x8cf30bad, 0x81b02d74, 0x857130c3,
0xd5b88683, 0xd1799b34, 0xdc3abded, 0xd8fba05a, 0x5d8a9099, 0x594b8d2e, 0x5408abf7, 0x50c9b640, 0x4e8ee645, 0x4a4ffbf2,
0x690ce0ee, 0x6dcdfd59, 0x608edb80, 0x644fc637, 0x470cdd2b, 0x43cdc09c, 0x7b827d21, 0x7f436096, 0x7200464f, 0x76c15bf8,
0x7a089632, 0x7ec98b85, 0x738aad5c, 0x774bb0eb, 0x68860bfd, 0x6c47164a, 0x61043093, 0x65c52d24, 0x119b4be9, 0x155a565e,
0x4f040d56, 0x4bc510e1, 0x46863638, 0x42472b8f, 0x18197087, 0x1cd86d30, 0x029f3d35, 0x065e2082, 0x0b1d065b, 0x0fdc1bec,
0x5c007b8a, 0x58c1663d, 0x558240e4, 0x51435d53, 0x3793a651, 0x3352bbe6, 0x3e119d3f, 0x3ad08088, 0x2497d08d, 0x2056cd3a,
0x251d3b9e, 0x21dc2629, 0x2c9f00f0, 0x285e1d47, 0x2d15ebe3, 0x29d4f654, 0xc5a92679, 0xc1683bce, 0xcc2b1d17, 0xc8ea00a0,
0x36194d42, 0x32d850f5, 0x3f9b762c, 0x3b5a6b9b, 0xd6ad50a5, 0xd26c4d12, 0xdf2f6bcb, 0xdbee767c, 0xe3a1cbc1, 0xe760d676,
0x0315d626, 0x07d4cb91, 0x0a97ed48, 0x0e56f0ff, 0xea23f0af, 0xeee2ed18, 0xf0a5bd1d, 0xf464a0aa, 0xf9278673, 0xfde69bc4,
0x1011a0fa, 0x14d0bd4d, 0x19939b94, 0x1d528623, 0x89b8fd09, 0x8d79e0be, 0x803ac667, 0x84fbdbd0, 0x9abc8bd5, 0x9e7d9662,
0xf12f560e, 0xf5ee4bb9, 0xf8ad6d60, 0xfc6c70d7, 0x933eb0bb, 0x97ffad0c, 0xafb010b1, 0xab710d06, 0xa6322bdf, 0xa2f33668,
0xe22b20d2, 0xe6ea3d65, 0xeba91bbc, 0xef68060b, 0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4,
0xd727bbb6, 0xd3e6a601, 0xdea580d8, 0xda649d6f,
0xc423cd6a, 0xc0e2d0dd, 0xcda1f604, 0xc960ebb3,
0xbd3e8d7e, 0xb9ff90c9, 0xb4bcb610, 0xb07daba7,
0xae3afba2, 0xaafbe615, 0xa7b8c0cc, 0xa379dd7b,
0x9b3660c6, 0x9ff77d71, 0x92b45ba8, 0x9675461f,
0x8832161a, 0x8cf30bad, 0x81b02d74, 0x857130c3,
0x5d8a9099, 0x594b8d2e, 0x5408abf7, 0x50c9b640,
0x4e8ee645, 0x4a4ffbf2, 0x470cdd2b, 0x43cdc09c,
0x7b827d21, 0x7f436096, 0x7200464f, 0x76c15bf8,
0x68860bfd, 0x6c47164a, 0x61043093, 0x65c52d24,
0x119b4be9, 0x155a565e, 0x18197087, 0x1cd86d30,
0x029f3d35, 0x065e2082, 0x0b1d065b, 0x0fdc1bec,
0x3793a651, 0x3352bbe6, 0x3e119d3f, 0x3ad08088,
0x2497d08d, 0x2056cd3a, 0x2d15ebe3, 0x29d4f654,
0xc5a92679, 0xc1683bce, 0xcc2b1d17, 0xc8ea00a0,
0xd6ad50a5, 0xd26c4d12, 0xdf2f6bcb, 0xdbee767c,
0xe3a1cbc1, 0xe760d676, 0xea23f0af, 0xeee2ed18,
0xf0a5bd1d, 0xf464a0aa, 0xf9278673, 0xfde69bc4,
0x89b8fd09, 0x8d79e0be, 0x803ac667, 0x84fbdbd0,
0x9abc8bd5, 0x9e7d9662, 0x933eb0bb, 0x97ffad0c,
0xafb010b1, 0xab710d06, 0xa6322bdf, 0xa2f33668,
0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4
]; ];
array = function(bytes) { // State arrays initialized in header()
var bit = 0, byte = 0; private byteCount!: Int32Array;
var BITMASK = [0, 0x01, 0x03, 0x07, 0x0F, 0x1F, 0x3F, 0x7F, 0xFF ]; private symToByte!: Uint8Array;
return function(n) { private mtfSymbol!: Int32Array;
var result = 0; private selectors!: Uint8Array;
while(n > 0) {
var left = 8 - bit; /**
* Create a bit reader from a byte array
*/
array(bytes: Uint8Array | Buffer): (n: number) => number {
let bit = 0;
let byte = 0;
const BITMASK = [0, 0x01, 0x03, 0x07, 0x0f, 0x1f, 0x3f, 0x7f, 0xff];
return function (n: number): number {
let result = 0;
while (n > 0) {
const left = 8 - bit;
if (n >= left) { if (n >= left) {
result <<= left; result <<= left;
result |= (BITMASK[left] & bytes[byte++]); result |= BITMASK[left] & bytes[byte++];
bit = 0; bit = 0;
n -= left; n -= left;
} else { } else {
result <<= n; result <<= n;
result |= ((bytes[byte] & (BITMASK[n] << (8 - n - bit))) >> (8 - n - bit)); result |= (bytes[byte] & (BITMASK[n] << (8 - n - bit))) >> (8 - n - bit);
bit += n; bit += n;
n = 0; n = 0;
} }
} }
return result; return result;
} };
} }
simple = function(srcbuffer, stream) { /**
var bits = this.array(srcbuffer); * Simple decompression from a buffer
var size = this.header(bits); */
var ret = false; simple(srcbuffer: Uint8Array | Buffer, stream: (byte: number) => void): void {
var bufsize = 100000 * size; const bits = this.array(srcbuffer);
var buf = new Int32Array(bufsize); const size = this.header(bits as IBitReader);
let ret: number | null = 0;
const bufsize = 100000 * size;
const buf = new Int32Array(bufsize);
do { do {
ret = this.decompress(bits, stream, buf, bufsize); ret = this.decompress(bits as IBitReader, stream, buf, bufsize, ret);
} while(!ret); } while (ret !== null);
} }
header = function(bits) { /**
* Parse BZIP2 header and return block size
*/
header(bits: IBitReader): number {
this.byteCount = new Int32Array(256); this.byteCount = new Int32Array(256);
this.symToByte = new Uint8Array(256); this.symToByte = new Uint8Array(256);
this.mtfSymbol = new Int32Array(256); this.mtfSymbol = new Int32Array(256);
this.selectors = new Uint8Array(0x8000); this.selectors = new Uint8Array(0x8000);
if (bits(8*3) != 4348520) messageArg.Error("No magic number found"); if (bits(8 * 3) !== 4348520) {
throwError('No BZIP2 magic number found at start of stream', BZIP2_ERROR_CODES.NO_MAGIC_NUMBER);
}
var i = bits(8) - 48; const blockSize = (bits(8) as number) - 48;
if (i < 1 || i > 9) messageArg.Error("Not a BZIP archive"); if (blockSize < 1 || blockSize > 9) {
return i; throwError('Invalid BZIP2 archive: block size must be 1-9', BZIP2_ERROR_CODES.INVALID_ARCHIVE);
}; }
return blockSize;
}
decompress = function(bits, stream, buf, bufsize, streamCRC) { /**
var MAX_HUFCODE_BITS = 20; * Decompress a BZIP2 block
var MAX_SYMBOLS = 258; */
var SYMBOL_RUNA = 0; decompress(
var SYMBOL_RUNB = 1; bits: IBitReader,
var GROUP_SIZE = 50; stream: (byte: number) => void,
var crc = 0 ^ (-1); buf: Int32Array,
bufsize: number,
streamCRC?: number | null
): number | null {
const MAX_HUFCODE_BITS = 20;
const MAX_SYMBOLS = 258;
const SYMBOL_RUNA = 0;
const SYMBOL_RUNB = 1;
const GROUP_SIZE = 50;
let crc = 0 ^ -1;
for(var h = '', i = 0; i < 6; i++) h += bits(8).toString(16); // Read block header
if (h == "177245385090") { let headerHex = '';
var finalCRC = bits(32)|0; for (let i = 0; i < 6; i++) {
if (finalCRC !== streamCRC) messageArg.Error("Error in bzip2: crc32 do not match"); headerHex += (bits(8) as number).toString(16);
// align stream to byte }
// Check for end-of-stream marker
if (headerHex === '177245385090') {
const finalCRC = bits(32) as number | 0;
if (finalCRC !== streamCRC) {
throwError('CRC32 mismatch: stream checksum verification failed', BZIP2_ERROR_CODES.CRC_MISMATCH);
}
// Align stream to byte boundary
bits(null); bits(null);
return null; // reset streamCRC for next call return null;
} }
if (h != "314159265359") messageArg.Error("eek not valid bzip data");
var crcblock = bits(32)|0; // CRC code // Verify block signature (pi digits)
if (bits(1)) messageArg.Error("unsupported obsolete version"); if (headerHex !== '314159265359') {
var origPtr = bits(24); throwError('Invalid block header: expected pi signature (0x314159265359)', BZIP2_ERROR_CODES.INVALID_BLOCK_DATA);
if (origPtr > bufsize) messageArg.Error("Initial position larger than buffer size"); }
var t = bits(16);
var symTotal = 0; const crcblock = bits(32) as number | 0;
for (i = 0; i < 16; i++) {
if (t & (1 << (15 - i))) { if (bits(1)) {
var k = bits(16); throwError('Unsupported obsolete BZIP2 format version', BZIP2_ERROR_CODES.INVALID_ARCHIVE);
for(j = 0; j < 16; j++) { }
if (k & (1 << (15 - j))) {
this.symToByte[symTotal++] = (16 * i) + j; const origPtr = bits(24) as number;
if (origPtr > bufsize) {
throwError('Initial position larger than buffer size', BZIP2_ERROR_CODES.BUFFER_OVERFLOW);
}
// Read symbol map
let symbolMapBits = bits(16) as number;
let symTotal = 0;
for (let i = 0; i < 16; i++) {
if (symbolMapBits & (1 << (15 - i))) {
const subMap = bits(16) as number;
for (let j = 0; j < 16; j++) {
if (subMap & (1 << (15 - j))) {
this.symToByte[symTotal++] = 16 * i + j;
} }
} }
} }
} }
var groupCount = bits(3); // Read Huffman groups
if (groupCount < 2 || groupCount > 6) messageArg.Error("another error"); const groupCount = bits(3) as number;
var nSelectors = bits(15); if (groupCount < 2 || groupCount > 6) {
if (nSelectors == 0) messageArg.Error("meh"); throwError('Invalid group count: must be between 2 and 6', BZIP2_ERROR_CODES.INVALID_HUFFMAN);
for(var i = 0; i < groupCount; i++) this.mtfSymbol[i] = i; }
for(var i = 0; i < nSelectors; i++) { const nSelectors = bits(15) as number;
for(var j = 0; bits(1); j++) if (j >= groupCount) messageArg.Error("whoops another error"); if (nSelectors === 0) {
var uc = this.mtfSymbol[j]; throwError('Invalid selector count: cannot be zero', BZIP2_ERROR_CODES.INVALID_SELECTOR);
for(var k: any = j-1; k>=0; k--) { }
this.mtfSymbol[k+1] = this.mtfSymbol[k];
// Initialize MTF symbol array
for (let i = 0; i < groupCount; i++) {
this.mtfSymbol[i] = i;
}
// Read selectors using MTF decoding
for (let i = 0; i < nSelectors; i++) {
let j = 0;
while (bits(1)) {
j++;
if (j >= groupCount) {
throwError('Invalid MTF index: exceeds group count', BZIP2_ERROR_CODES.INVALID_HUFFMAN);
}
}
const uc = this.mtfSymbol[j];
for (let k = j - 1; k >= 0; k--) {
this.mtfSymbol[k + 1] = this.mtfSymbol[k];
} }
this.mtfSymbol[0] = uc; this.mtfSymbol[0] = uc;
this.selectors[i] = uc; this.selectors[i] = uc;
} }
var symCount = symTotal + 2; // Build Huffman tables
var groups = []; const symCount = symTotal + 2;
var length = new Uint8Array(MAX_SYMBOLS), const groups: IHuffmanGroup[] = [];
temp = new Uint16Array(MAX_HUFCODE_BITS+1); const length = new Uint8Array(MAX_SYMBOLS);
const temp = new Uint16Array(MAX_HUFCODE_BITS + 1);
var hufGroup; for (let j = 0; j < groupCount; j++) {
let t = bits(5) as number;
for(var j = 0; j < groupCount; j++) { for (let i = 0; i < symCount; i++) {
t = bits(5); //lengths while (true) {
for(var i = 0; i < symCount; i++) { if (t < 1 || t > MAX_HUFCODE_BITS) {
while(true){ throwError('Invalid Huffman code length: must be between 1 and 20', BZIP2_ERROR_CODES.INVALID_HUFFMAN);
if (t < 1 || t > MAX_HUFCODE_BITS) messageArg.Error("I gave up a while ago on writing error messages"); }
if (!bits(1)) break; if (!bits(1)) break;
if (!bits(1)) t++; if (!bits(1)) t++;
else t--; else t--;
} }
length[i] = t; length[i] = t;
} }
var minLen, maxLen;
minLen = maxLen = length[0]; let minLen = length[0];
for(var i = 1; i < symCount; i++) { let maxLen = length[0];
for (let i = 1; i < symCount; i++) {
if (length[i] > maxLen) maxLen = length[i]; if (length[i] > maxLen) maxLen = length[i];
else if (length[i] < minLen) minLen = length[i]; else if (length[i] < minLen) minLen = length[i];
} }
hufGroup = groups[j] = {};
hufGroup.permute = new Int32Array(MAX_SYMBOLS);
hufGroup.limit = new Int32Array(MAX_HUFCODE_BITS + 1);
hufGroup.base = new Int32Array(MAX_HUFCODE_BITS + 1);
hufGroup.minLen = minLen; const hufGroup: IHuffmanGroup = {
hufGroup.maxLen = maxLen; permute: new Int32Array(MAX_SYMBOLS),
var base = hufGroup.base; limit: new Int32Array(MAX_HUFCODE_BITS + 1),
var limit = hufGroup.limit; base: new Int32Array(MAX_HUFCODE_BITS + 1),
var pp = 0; minLen,
for(var i: number = minLen; i <= maxLen; i++) maxLen,
for(var t: any = 0; t < symCount; t++) };
if (length[t] == i) hufGroup.permute[pp++] = t; groups[j] = hufGroup;
for(i = minLen; i <= maxLen; i++) temp[i] = limit[i] = 0;
for(i = 0; i < symCount; i++) temp[length[i]]++; const base = hufGroup.base;
pp = t = 0; const limit = hufGroup.limit;
for(i = minLen; i < maxLen; i++) {
let pp = 0;
for (let i = minLen; i <= maxLen; i++) {
for (let t = 0; t < symCount; t++) {
if (length[t] === i) hufGroup.permute[pp++] = t;
}
}
for (let i = minLen; i <= maxLen; i++) {
temp[i] = 0;
limit[i] = 0;
}
for (let i = 0; i < symCount; i++) {
temp[length[i]]++;
}
pp = 0;
let tt = 0;
for (let i = minLen; i < maxLen; i++) {
pp += temp[i]; pp += temp[i];
limit[i] = pp - 1; limit[i] = pp - 1;
pp <<= 1; pp <<= 1;
base[i+1] = pp - (t += temp[i]); base[i + 1] = pp - (tt += temp[i]);
} }
limit[maxLen] = pp + temp[maxLen] - 1; limit[maxLen] = pp + temp[maxLen] - 1;
base[minLen] = 0; base[minLen] = 0;
} }
for(var i = 0; i < 256; i++) { // Initialize for decoding
for (let i = 0; i < 256; i++) {
this.mtfSymbol[i] = i; this.mtfSymbol[i] = i;
this.byteCount[i] = 0; this.byteCount[i] = 0;
} }
var runPos, count, symCount: number, selector;
runPos = count = symCount = selector = 0; let runPos = 0;
while(true) { let count = 0;
if (!(symCount--)) { let symCountRemaining = 0;
symCount = GROUP_SIZE - 1; let selector = 0;
if (selector >= nSelectors) messageArg.Error("meow i'm a kitty, that's an error"); let hufGroup = groups[0];
let base = hufGroup.base;
let limit = hufGroup.limit;
// Main decoding loop
while (true) {
if (!symCountRemaining--) {
symCountRemaining = GROUP_SIZE - 1;
if (selector >= nSelectors) {
throwError('Invalid selector index: exceeds available groups', BZIP2_ERROR_CODES.INVALID_SELECTOR);
}
hufGroup = groups[this.selectors[selector++]]; hufGroup = groups[this.selectors[selector++]];
base = hufGroup.base; base = hufGroup.base;
limit = hufGroup.limit; limit = hufGroup.limit;
} }
i = hufGroup.minLen;
j = bits(i); let i = hufGroup.minLen;
while(true) { let j = bits(i) as number;
if (i > hufGroup.maxLen) messageArg.Error("rawr i'm a dinosaur");
while (true) {
if (i > hufGroup.maxLen) {
throwError('Huffman decoding error: bit length exceeds maximum allowed', BZIP2_ERROR_CODES.INVALID_HUFFMAN);
}
if (j <= limit[i]) break; if (j <= limit[i]) break;
i++; i++;
j = (j << 1) | bits(1); j = (j << 1) | (bits(1) as number);
} }
j -= base[i]; j -= base[i];
if (j < 0 || j >= MAX_SYMBOLS) messageArg.Error("moo i'm a cow"); if (j < 0 || j >= MAX_SYMBOLS) {
var nextSym = hufGroup.permute[j]; throwError('Symbol index out of bounds during Huffman decoding', BZIP2_ERROR_CODES.INVALID_HUFFMAN);
if (nextSym == SYMBOL_RUNA || nextSym == SYMBOL_RUNB) {
if (!runPos){
runPos = 1;
t = 0;
} }
if (nextSym == SYMBOL_RUNA) t += runPos;
else t += 2 * runPos; const nextSym = hufGroup.permute[j];
if (nextSym === SYMBOL_RUNA || nextSym === SYMBOL_RUNB) {
if (!runPos) {
runPos = 1;
j = 0;
}
if (nextSym === SYMBOL_RUNA) j += runPos;
else j += 2 * runPos;
runPos <<= 1; runPos <<= 1;
continue; continue;
} }
if (runPos) { if (runPos) {
runPos = 0; runPos = 0;
if (count + t > bufsize) messageArg.Error("Boom."); const runLength = j;
uc = this.symToByte[this.mtfSymbol[0]]; if (count + runLength > bufsize) {
this.byteCount[uc] += t; throwError('Run-length overflow: decoded run exceeds buffer capacity', BZIP2_ERROR_CODES.BUFFER_OVERFLOW);
while(t--) buf[count++] = uc;
} }
if (nextSym > symTotal) break; const uc = this.symToByte[this.mtfSymbol[0]];
if (count >= bufsize) messageArg.Error("I can't think of anything. Error"); this.byteCount[uc] += runLength;
i = nextSym - 1; for (let t = 0; t < runLength; t++) {
uc = this.mtfSymbol[i];
for(var k: any = i-1; k>=0; k--) {
this.mtfSymbol[k+1] = this.mtfSymbol[k];
}
this.mtfSymbol[0] = uc
uc = this.symToByte[uc];
this.byteCount[uc]++;
buf[count++] = uc; buf[count++] = uc;
} }
if (origPtr < 0 || origPtr >= count) messageArg.Error("I'm a monkey and I'm throwing something at someone, namely you"); }
var j = 0;
for(var i = 0; i < 256; i++) { if (nextSym > symTotal) break;
k = j + this.byteCount[i];
if (count >= bufsize) {
throwError('Buffer overflow: decoded data exceeds buffer capacity', BZIP2_ERROR_CODES.BUFFER_OVERFLOW);
}
const mtfIndex = nextSym - 1;
const uc = this.mtfSymbol[mtfIndex];
for (let k = mtfIndex - 1; k >= 0; k--) {
this.mtfSymbol[k + 1] = this.mtfSymbol[k];
}
this.mtfSymbol[0] = uc;
const decodedByte = this.symToByte[uc];
this.byteCount[decodedByte]++;
buf[count++] = decodedByte;
}
if (origPtr < 0 || origPtr >= count) {
throwError('Invalid original pointer: position outside decoded block', BZIP2_ERROR_CODES.INVALID_POSITION);
}
// Inverse BWT transform
let j = 0;
for (let i = 0; i < 256; i++) {
const k = j + this.byteCount[i];
this.byteCount[i] = j; this.byteCount[i] = j;
j = k; j = k;
} }
for(var i = 0; i < count; i++) {
uc = buf[i] & 0xff; for (let i = 0; i < count; i++) {
buf[this.byteCount[uc]] |= (i << 8); const uc = buf[i] & 0xff;
buf[this.byteCount[uc]] |= i << 8;
this.byteCount[uc]++; this.byteCount[uc]++;
} }
var pos = 0, current = 0, run = 0;
// Output decoded data
let pos = 0;
let current = 0;
let run = 0;
if (count) { if (count) {
pos = buf[origPtr]; pos = buf[origPtr];
current = (pos & 0xff); current = pos & 0xff;
pos >>= 8; pos >>= 8;
run = -1; run = -1;
} }
count = count;
var copies, previous, outbyte; let remaining = count;
while(count) { while (remaining) {
count--; remaining--;
previous = current; const previous = current;
pos = buf[pos]; pos = buf[pos];
current = pos & 0xff; current = pos & 0xff;
pos >>= 8; pos >>= 8;
if (run++ == 3) {
let copies: number;
let outbyte: number;
if (run++ === 3) {
copies = current; copies = current;
outbyte = previous; outbyte = previous;
current = -1; current = -1;
@@ -320,16 +429,21 @@ export class Bzip2 {
copies = 1; copies = 1;
outbyte = current; outbyte = current;
} }
while(copies--) {
crc = ((crc << 8) ^ this.crcTable[((crc>>24) ^ outbyte) & 0xFF])&0xFFFFFFFF; // crc32 while (copies--) {
crc = ((crc << 8) ^ this.crcTable[((crc >> 24) ^ outbyte) & 0xff]) & 0xffffffff;
stream(outbyte); stream(outbyte);
} }
if (current != previous) run = 0;
if (current !== previous) run = 0;
} }
crc = (crc ^ (-1)) >>> 0; crc = (crc ^ -1) >>> 0;
if ((crc|0) != (crcblock|0)) messageArg.Error("Error in bzip2: crc32 do not match"); if ((crc | 0) !== (crcblock | 0)) {
streamCRC = (crc ^ ((streamCRC << 1) | (streamCRC >>> 31))) & 0xFFFFFFFF; throwError('CRC32 mismatch: block checksum verification failed', BZIP2_ERROR_CODES.CRC_MISMATCH);
return streamCRC; }
};
}; const newStreamCRC = (crc ^ (((streamCRC || 0) << 1) | ((streamCRC || 0) >>> 31))) & 0xffffffff;
return newStreamCRC;
}
}

View File

@@ -1,45 +1,53 @@
import * as plugins from '../plugins.js'; import * as plugins from '../plugins.js';
import { Bzip2Error, BZIP2_ERROR_CODES } from '../errors.js';
import type { IBitReader } from '../interfaces.js';
import { Bzip2 } from './bzip2.js'; import { Bzip2 } from './bzip2.js';
import { bitIterator } from './bititerator.js'; import { bitIterator } from './bititerator.js';
export function unbzip2Stream() { /**
* Creates a streaming BZIP2 decompression transform
*/
export function unbzip2Stream(): plugins.smartstream.SmartDuplex<Buffer, Buffer> {
const bzip2Instance = new Bzip2(); const bzip2Instance = new Bzip2();
var bufferQueue = []; const bufferQueue: Buffer[] = [];
var hasBytes = 0; let hasBytes = 0;
var blockSize = 0; let blockSize = 0;
var broken = false; let broken = false;
var done = false; let bitReader: IBitReader | null = null;
var bitReader = null; let streamCRC: number | null = null;
var streamCRC = null;
function decompressBlock() { function decompressBlock(): Buffer | undefined {
if (!blockSize) { if (!blockSize) {
blockSize = bzip2Instance.header(bitReader); blockSize = bzip2Instance.header(bitReader!);
streamCRC = 0; streamCRC = 0;
} else { return undefined;
var bufsize = 100000 * blockSize; }
var buf = new Int32Array(bufsize);
var chunk = []; const bufsize = 100000 * blockSize;
var f = function (b) { const buf = new Int32Array(bufsize);
const chunk: number[] = [];
const outputFunc = (b: number): void => {
chunk.push(b); chunk.push(b);
}; };
streamCRC = bzip2Instance.decompress(bitReader, f, buf, bufsize, streamCRC); streamCRC = bzip2Instance.decompress(bitReader!, outputFunc, buf, bufsize, streamCRC);
if (streamCRC === null) { if (streamCRC === null) {
// reset for next bzip2 header // Reset for next bzip2 header
blockSize = 0; blockSize = 0;
return; return undefined;
} else {
return Buffer.from(chunk);
}
}
} }
var outlength = 0; return Buffer.from(chunk);
const decompressAndPush = async () => { }
if (broken) return;
let outlength = 0;
const decompressAndPush = async (): Promise<Buffer | undefined> => {
if (broken) return undefined;
try { try {
const resultChunk = decompressBlock(); const resultChunk = decompressBlock();
if (resultChunk) { if (resultChunk) {
@@ -47,38 +55,51 @@ export function unbzip2Stream() {
} }
return resultChunk; return resultChunk;
} catch (e) { } catch (e) {
console.error(e);
broken = true; broken = true;
return false; if (e instanceof Error) {
throw new Bzip2Error(`Decompression failed: ${e.message}`, BZIP2_ERROR_CODES.INVALID_BLOCK_DATA);
}
throw e;
} }
}; };
return new plugins.smartstream.SmartDuplex({ return new plugins.smartstream.SmartDuplex<Buffer, Buffer>({
objectMode: true,
name: 'bzip2',
highWaterMark: 1,
writeFunction: async function (data, streamTools) { writeFunction: async function (data, streamTools) {
//console.error('received', data.length,'bytes in', typeof data);
bufferQueue.push(data); bufferQueue.push(data);
hasBytes += data.length; hasBytes += data.length;
if (bitReader === null) { if (bitReader === null) {
bitReader = bitIterator(function () { bitReader = bitIterator(function () {
return bufferQueue.shift(); return bufferQueue.shift()!;
}); });
} }
while (!broken && hasBytes - bitReader.bytesRead + 1 >= (25000 + 100000 * blockSize || 4)) {
//console.error('decompressing with', hasBytes - bitReader.bytesRead + 1, 'bytes in buffer'); const threshold = 25000 + 100000 * blockSize || 4;
while (!broken && hasBytes - bitReader.bytesRead + 1 >= threshold) {
const result = await decompressAndPush(); const result = await decompressAndPush();
if (!result) {
continue;
}
await streamTools.push(result); await streamTools.push(result);
} }
return null;
}, },
finalFunction: async function (streamTools) { finalFunction: async function (streamTools) {
//console.error(x,'last compressing with', hasBytes, 'bytes in buffer');
while (!broken && bitReader && hasBytes > bitReader.bytesRead) { while (!broken && bitReader && hasBytes > bitReader.bytesRead) {
const result = await decompressAndPush(); const result = await decompressAndPush();
streamTools.push(result); if (!result) {
continue;
} }
if (!broken) { await streamTools.push(result);
if (streamCRC !== null) this.emit('error', new Error('input stream ended prematurely'));
this.queue(null);
} }
if (!broken && streamCRC !== null) {
this.emit('error', new Bzip2Error('Input stream ended prematurely', BZIP2_ERROR_CODES.PREMATURE_END));
}
return null;
}, },
}); });
} }

View File

@@ -1,21 +1,41 @@
import type { SmartArchive } from './classes.smartarchive.js'; import type { SmartArchive } from './classes.smartarchive.js';
import type { TSupportedMime } from './interfaces.js';
import * as plugins from './plugins.js'; import * as plugins from './plugins.js';
/**
* Type for decompression streams
*/
export type TDecompressionStream =
| plugins.stream.Transform
| plugins.stream.Duplex
| plugins.tarStream.Extract;
/**
* Result of archive analysis
*/
export interface IAnalyzedResult { export interface IAnalyzedResult {
fileType: plugins.fileType.FileTypeResult; fileType: plugins.fileType.FileTypeResult | undefined;
isArchive: boolean; isArchive: boolean;
resultStream: plugins.smartstream.PassThrough; resultStream: plugins.smartstream.SmartDuplex<Buffer, Buffer>;
decompressionStream: plugins.stream.Transform | plugins.stream.Duplex | plugins.tarStream.Extract; decompressionStream: TDecompressionStream;
} }
/**
* Analyzes archive streams to detect format and provide decompression
*/
export class ArchiveAnalyzer { export class ArchiveAnalyzer {
smartArchiveRef: SmartArchive; private smartArchiveRef: SmartArchive;
constructor(smartArchiveRefArg: SmartArchive) { constructor(smartArchiveRefArg: SmartArchive) {
this.smartArchiveRef = smartArchiveRefArg; this.smartArchiveRef = smartArchiveRefArg;
} }
private async mimeTypeIsArchive(mimeType: string): Promise<boolean> { /**
* Check if a MIME type represents an archive format
*/
private async mimeTypeIsArchive(mimeType: string | undefined): Promise<boolean> {
if (!mimeType) return false;
const archiveMimeTypes: Set<string> = new Set([ const archiveMimeTypes: Set<string> = new Set([
'application/zip', 'application/zip',
'application/x-rar-compressed', 'application/x-rar-compressed',
@@ -23,56 +43,63 @@ export class ArchiveAnalyzer {
'application/gzip', 'application/gzip',
'application/x-7z-compressed', 'application/x-7z-compressed',
'application/x-bzip2', 'application/x-bzip2',
// Add other archive mime types here
]); ]);
return archiveMimeTypes.has(mimeType); return archiveMimeTypes.has(mimeType);
} }
/**
private async getDecompressionStream( * Get the appropriate decompression stream for a MIME type
mimeTypeArg: plugins.fileType.FileTypeResult['mime'] */
): Promise<plugins.stream.Transform | plugins.stream.Duplex | plugins.tarStream.Extract> { private async getDecompressionStream(mimeTypeArg: TSupportedMime): Promise<TDecompressionStream> {
switch (mimeTypeArg) { switch (mimeTypeArg) {
case 'application/gzip': case 'application/gzip':
return this.smartArchiveRef.gzipTools.getDecompressionStream(); return this.smartArchiveRef.gzipTools.getDecompressionStream();
case 'application/zip':
return this.smartArchiveRef.zipTools.getDecompressionStream();
case 'application/x-bzip2': case 'application/x-bzip2':
return await this.smartArchiveRef.bzip2Tools.getDecompressionStream(); // replace with your own bzip2 decompression stream return this.smartArchiveRef.bzip2Tools.getDecompressionStream();
case 'application/x-tar': case 'application/x-tar':
return this.smartArchiveRef.tarTools.getDecompressionStream(); // replace with your own tar decompression stream return this.smartArchiveRef.tarTools.getDecompressionStream();
default: default:
// Handle unsupported formats or no decompression needed // Handle unsupported formats or no decompression needed
return new plugins.smartstream.PassThrough(); return plugins.smartstream.createPassThrough();
} }
} }
public getAnalyzedStream() { /**
* Create an analyzed stream that detects archive type and provides decompression
* Emits a single IAnalyzedResult object
*/
public getAnalyzedStream(): plugins.smartstream.SmartDuplex<Buffer, IAnalyzedResult> {
let firstRun = true; let firstRun = true;
const resultStream = new plugins.smartstream.PassThrough(); const resultStream = plugins.smartstream.createPassThrough();
const analyzerstream = new plugins.smartstream.SmartDuplex<Buffer, IAnalyzedResult>({ const analyzerstream = new plugins.smartstream.SmartDuplex<Buffer, IAnalyzedResult>({
readableObjectMode: true, readableObjectMode: true,
writeFunction: async (chunkArg: Buffer, streamtools) => { writeFunction: async (chunkArg: Buffer, streamtools) => {
const fileType = await plugins.fileType.fileTypeFromBuffer(chunkArg);
const decompressionStream = await this.getDecompressionStream(fileType?.mime as any);
resultStream.push(chunkArg);
if (firstRun) { if (firstRun) {
firstRun = false; firstRun = false;
const fileType = await plugins.fileType.fileTypeFromBuffer(chunkArg);
const decompressionStream = await this.getDecompressionStream(fileType?.mime as TSupportedMime);
const result: IAnalyzedResult = { const result: IAnalyzedResult = {
fileType, fileType,
isArchive: await this.mimeTypeIsArchive(fileType?.mime), isArchive: await this.mimeTypeIsArchive(fileType?.mime),
resultStream, resultStream,
decompressionStream, decompressionStream,
}; };
streamtools.push(result); await streamtools.push(result);
streamtools.push(null);
return null;
} }
await resultStream.backpressuredPush(chunkArg);
return null;
}, },
finalFunction: async (tools) => { finalFunction: async () => {
resultStream.push(null); resultStream.push(null);
return null; return null;
} },
}); });
return analyzerstream; return analyzerstream;
} }
} }

View File

@@ -1,59 +1,143 @@
import type { SmartArchive } from './classes.smartarchive.js'; import * as plugins from './plugins.js';
import * as plugins from './plugins.js' import type { TCompressionLevel } from './interfaces.js';
// This class wraps fflate's gunzip in a Node.js Transform stream /**
export class CompressGunzipTransform extends plugins.stream.Transform { * Transform stream for GZIP compression using fflate
constructor() { */
export class GzipCompressionTransform extends plugins.stream.Transform {
private gzip: plugins.fflate.Gzip;
constructor(level: TCompressionLevel = 6) {
super(); super();
}
_transform(chunk: Buffer, encoding: BufferEncoding, callback: plugins.stream.TransformCallback) { // Create a streaming Gzip compressor
plugins.fflate.gunzip(chunk, (err, decompressed) => { this.gzip = new plugins.fflate.Gzip({ level }, (chunk, final) => {
if (err) { this.push(Buffer.from(chunk));
callback(err); if (final) {
} else { this.push(null);
this.push(decompressed);
callback();
} }
}); });
} }
}
// DecompressGunzipTransform class that extends the Node.js Transform stream to _transform(
// create a stream that decompresses GZip-compressed data using fflate's gunzip function chunk: Buffer,
export class DecompressGunzipTransform extends plugins.stream.Transform { encoding: BufferEncoding,
constructor() { callback: plugins.stream.TransformCallback
super(); ): void {
try {
this.gzip.push(chunk, false);
callback();
} catch (err) {
callback(err as Error);
}
} }
_transform(chunk: Buffer, encoding: BufferEncoding, callback: plugins.stream.TransformCallback) { _flush(callback: plugins.stream.TransformCallback): void {
// Use fflate's gunzip function to decompress the chunk try {
plugins.fflate.gunzip(chunk, (err, decompressed) => { this.gzip.push(new Uint8Array(0), true);
if (err) {
// If an error occurs during decompression, pass the error to the callback
callback(err);
} else {
// If decompression is successful, push the decompressed data into the stream
this.push(decompressed);
callback(); callback();
} catch (err) {
callback(err as Error);
}
}
}
/**
* Transform stream for GZIP decompression using fflate
*/
export class GzipDecompressionTransform extends plugins.stream.Transform {
private gunzip: plugins.fflate.Gunzip;
constructor() {
super();
// Create a streaming Gunzip decompressor
this.gunzip = new plugins.fflate.Gunzip((chunk, final) => {
this.push(Buffer.from(chunk));
if (final) {
this.push(null);
} }
}); });
} }
_transform(
chunk: Buffer,
encoding: BufferEncoding,
callback: plugins.stream.TransformCallback
): void {
try {
this.gunzip.push(chunk, false);
callback();
} catch (err) {
callback(err as Error);
}
}
_flush(callback: plugins.stream.TransformCallback): void {
try {
this.gunzip.push(new Uint8Array(0), true);
callback();
} catch (err) {
callback(err as Error);
}
}
} }
/**
* GZIP compression and decompression utilities
*/
export class GzipTools { export class GzipTools {
smartArchiveRef: SmartArchive; /**
* Get a streaming compression transform
constructor(smartArchiveRefArg: SmartArchive) { */
this.smartArchiveRef = smartArchiveRefArg; public getCompressionStream(level?: TCompressionLevel): plugins.stream.Transform {
return new GzipCompressionTransform(level);
} }
public getCompressionStream() { /**
return new CompressGunzipTransform(); * Get a streaming decompression transform
*/
public getDecompressionStream(): plugins.stream.Transform {
return new GzipDecompressionTransform();
} }
public getDecompressionStream() { /**
return new DecompressGunzipTransform(); * Compress data synchronously
*/
public compressSync(data: Buffer, level?: TCompressionLevel): Buffer {
const options = level !== undefined ? { level } : undefined;
return Buffer.from(plugins.fflate.gzipSync(data, options));
}
/**
* Decompress data synchronously
*/
public decompressSync(data: Buffer): Buffer {
return Buffer.from(plugins.fflate.gunzipSync(data));
}
/**
* Compress data asynchronously
*/
public async compress(data: Buffer, level?: TCompressionLevel): Promise<Buffer> {
return new Promise((resolve, reject) => {
const options = level !== undefined ? { level } : undefined;
plugins.fflate.gzip(data, options as plugins.fflate.AsyncGzipOptions, (err, result) => {
if (err) reject(err);
else resolve(Buffer.from(result));
});
});
}
/**
* Decompress data asynchronously
*/
public async decompress(data: Buffer): Promise<Buffer> {
return new Promise((resolve, reject) => {
plugins.fflate.gunzip(data, (err, result) => {
if (err) reject(err);
else resolve(Buffer.from(result));
});
});
} }
} }

View File

@@ -1,29 +1,51 @@
import * as plugins from './plugins.js'; import * as plugins from './plugins.js';
import * as paths from './paths.js'; import type {
IArchiveCreationOptions,
IArchiveEntry,
IArchiveExtractionOptions,
IArchiveEntryInfo,
IArchiveInfo,
TArchiveFormat,
TCompressionLevel,
} from './interfaces.js';
import { Bzip2Tools } from './classes.bzip2tools.js';
import { GzipTools } from './classes.gziptools.js'; import { GzipTools } from './classes.gziptools.js';
import { TarTools } from './classes.tartools.js'; import { TarTools } from './classes.tartools.js';
import { Bzip2Tools } from './classes.bzip2tools.js'; import { ZipTools } from './classes.ziptools.js';
import { ArchiveAnalyzer, type IAnalyzedResult } from './classes.archiveanalyzer.js'; import { ArchiveAnalyzer, type IAnalyzedResult } from './classes.archiveanalyzer.js';
import type { from } from '@push.rocks/smartrx/dist_ts/smartrx.plugins.rxjs.js'; /**
* Main class for archive manipulation
* Supports TAR, ZIP, GZIP, and BZIP2 formats
*/
export class SmartArchive { export class SmartArchive {
// STATIC // ============================================
public static async fromArchiveUrl(urlArg: string): Promise<SmartArchive> { // STATIC FACTORY METHODS - EXTRACTION
// ============================================
/**
* Create SmartArchive from a URL
*/
public static async fromUrl(urlArg: string): Promise<SmartArchive> {
const smartArchiveInstance = new SmartArchive(); const smartArchiveInstance = new SmartArchive();
smartArchiveInstance.sourceUrl = urlArg; smartArchiveInstance.sourceUrl = urlArg;
return smartArchiveInstance; return smartArchiveInstance;
} }
public static async fromArchiveFile(filePathArg: string): Promise<SmartArchive> { /**
* Create SmartArchive from a local file path
*/
public static async fromFile(filePathArg: string): Promise<SmartArchive> {
const smartArchiveInstance = new SmartArchive(); const smartArchiveInstance = new SmartArchive();
smartArchiveInstance.sourceFilePath = filePathArg; smartArchiveInstance.sourceFilePath = filePathArg;
return smartArchiveInstance; return smartArchiveInstance;
} }
public static async fromArchiveStream( /**
* Create SmartArchive from a readable stream
*/
public static async fromStream(
streamArg: plugins.stream.Readable | plugins.stream.Duplex | plugins.stream.Transform streamArg: plugins.stream.Readable | plugins.stream.Duplex | plugins.stream.Transform
): Promise<SmartArchive> { ): Promise<SmartArchive> {
const smartArchiveInstance = new SmartArchive(); const smartArchiveInstance = new SmartArchive();
@@ -31,105 +53,377 @@ export class SmartArchive {
return smartArchiveInstance; return smartArchiveInstance;
} }
// INSTANCE /**
public tarTools = new TarTools(this); * Create SmartArchive from an in-memory buffer
public gzipTools = new GzipTools(this); */
public static async fromBuffer(buffer: Buffer): Promise<SmartArchive> {
const smartArchiveInstance = new SmartArchive();
smartArchiveInstance.sourceStream = plugins.stream.Readable.from(buffer);
return smartArchiveInstance;
}
// ============================================
// STATIC FACTORY METHODS - CREATION
// ============================================
/**
* Create a new archive from a directory
*/
public static async fromDirectory(
directoryPath: string,
options: IArchiveCreationOptions
): Promise<SmartArchive> {
const smartArchiveInstance = new SmartArchive();
smartArchiveInstance.creationOptions = options;
const tarTools = new TarTools();
if (options.format === 'tar' || options.format === 'tar.gz' || options.format === 'tgz') {
if (options.format === 'tar') {
const pack = await tarTools.packDirectory(directoryPath);
pack.finalize();
smartArchiveInstance.archiveBuffer = await SmartArchive.streamToBuffer(pack);
} else {
smartArchiveInstance.archiveBuffer = await tarTools.packDirectoryToTarGz(
directoryPath,
options.compressionLevel
);
}
} else if (options.format === 'zip') {
const zipTools = new ZipTools();
const fileTree = await plugins.listFileTree(directoryPath, '**/*');
const entries: IArchiveEntry[] = [];
for (const filePath of fileTree) {
const absolutePath = plugins.path.join(directoryPath, filePath);
const content = await plugins.fsPromises.readFile(absolutePath);
entries.push({
archivePath: filePath,
content,
});
}
smartArchiveInstance.archiveBuffer = await zipTools.createZip(entries, options.compressionLevel);
} else {
throw new Error(`Unsupported format for directory packing: ${options.format}`);
}
return smartArchiveInstance;
}
/**
* Create a new archive from an array of entries
*/
public static async fromFiles(
files: IArchiveEntry[],
options: IArchiveCreationOptions
): Promise<SmartArchive> {
const smartArchiveInstance = new SmartArchive();
smartArchiveInstance.creationOptions = options;
if (options.format === 'tar' || options.format === 'tar.gz' || options.format === 'tgz') {
const tarTools = new TarTools();
if (options.format === 'tar') {
smartArchiveInstance.archiveBuffer = await tarTools.packFiles(files);
} else {
smartArchiveInstance.archiveBuffer = await tarTools.packFilesToTarGz(files, options.compressionLevel);
}
} else if (options.format === 'zip') {
const zipTools = new ZipTools();
smartArchiveInstance.archiveBuffer = await zipTools.createZip(files, options.compressionLevel);
} else if (options.format === 'gz') {
if (files.length !== 1) {
throw new Error('GZIP format only supports a single file');
}
const gzipTools = new GzipTools();
let content: Buffer;
if (typeof files[0].content === 'string') {
content = Buffer.from(files[0].content);
} else if (Buffer.isBuffer(files[0].content)) {
content = files[0].content;
} else {
throw new Error('GZIP format requires string or Buffer content');
}
smartArchiveInstance.archiveBuffer = await gzipTools.compress(content, options.compressionLevel);
} else {
throw new Error(`Unsupported format: ${options.format}`);
}
return smartArchiveInstance;
}
/**
* Start building an archive incrementally using a builder pattern
*/
public static create(options: IArchiveCreationOptions): SmartArchive {
const smartArchiveInstance = new SmartArchive();
smartArchiveInstance.creationOptions = options;
smartArchiveInstance.pendingEntries = [];
return smartArchiveInstance;
}
/**
* Helper to convert a stream to buffer
*/
private static async streamToBuffer(stream: plugins.stream.Readable): Promise<Buffer> {
const chunks: Buffer[] = [];
return new Promise((resolve, reject) => {
stream.on('data', (chunk) => chunks.push(Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk)));
stream.on('end', () => resolve(Buffer.concat(chunks)));
stream.on('error', reject);
});
}
// ============================================
// INSTANCE PROPERTIES
// ============================================
public tarTools = new TarTools();
public zipTools = new ZipTools();
public gzipTools = new GzipTools();
public bzip2Tools = new Bzip2Tools(this); public bzip2Tools = new Bzip2Tools(this);
public archiveAnalyzer = new ArchiveAnalyzer(this); public archiveAnalyzer = new ArchiveAnalyzer(this);
public sourceUrl: string; public sourceUrl?: string;
public sourceFilePath: string; public sourceFilePath?: string;
public sourceStream: plugins.stream.Readable | plugins.stream.Duplex | plugins.stream.Transform; public sourceStream?: plugins.stream.Readable | plugins.stream.Duplex | plugins.stream.Transform;
public archiveName: string; private archiveBuffer?: Buffer;
public singleFileMode: boolean = false; private creationOptions?: IArchiveCreationOptions;
private pendingEntries?: IArchiveEntry[];
public addedDirectories: string[] = [];
public addedFiles: (plugins.smartfile.SmartFile | plugins.smartfile.StreamFile)[] = [];
public addedUrls: string[] = [];
constructor() {} constructor() {}
// ============================================
// BUILDER METHODS (for incremental creation)
// ============================================
/** /**
* gets the original archive stream * Add a file to the archive (builder pattern)
*/ */
public async getArchiveStream() { public addFile(archivePath: string, content: string | Buffer): this {
if (!this.pendingEntries) {
throw new Error('addFile can only be called on archives created with SmartArchive.create()');
}
this.pendingEntries.push({ archivePath, content });
return this;
}
/**
* Add a SmartFile to the archive (builder pattern)
*/
public addSmartFile(file: plugins.smartfile.SmartFile, archivePath?: string): this {
if (!this.pendingEntries) {
throw new Error('addSmartFile can only be called on archives created with SmartArchive.create()');
}
this.pendingEntries.push({
archivePath: archivePath || file.relative,
content: file,
});
return this;
}
/**
* Add a StreamFile to the archive (builder pattern)
*/
public addStreamFile(file: plugins.smartfile.StreamFile, archivePath?: string): this {
if (!this.pendingEntries) {
throw new Error('addStreamFile can only be called on archives created with SmartArchive.create()');
}
this.pendingEntries.push({
archivePath: archivePath || file.relativeFilePath,
content: file,
});
return this;
}
/**
* Build the archive from pending entries
*/
public async build(): Promise<SmartArchive> {
if (!this.pendingEntries || !this.creationOptions) {
throw new Error('build can only be called on archives created with SmartArchive.create()');
}
const built = await SmartArchive.fromFiles(this.pendingEntries, this.creationOptions);
this.archiveBuffer = built.archiveBuffer;
this.pendingEntries = undefined;
return this;
}
// ============================================
// EXTRACTION METHODS
// ============================================
/**
* Get the original archive stream
*/
public async toStream(): Promise<plugins.stream.Readable> {
if (this.archiveBuffer) {
return plugins.stream.Readable.from(this.archiveBuffer);
}
if (this.sourceStream) { if (this.sourceStream) {
return this.sourceStream; return this.sourceStream;
} }
if (this.sourceUrl) { if (this.sourceUrl) {
const urlStream = await plugins.smartrequest.getStream(this.sourceUrl); const response = await plugins.smartrequest.SmartRequest.create()
return urlStream; .url(this.sourceUrl)
.get();
const webStream = response.stream();
return plugins.stream.Readable.fromWeb(webStream as any);
} }
if (this.sourceFilePath) { if (this.sourceFilePath) {
const fileStream = plugins.smartfile.fs.toReadStream(this.sourceFilePath); return plugins.fs.createReadStream(this.sourceFilePath);
return fileStream;
} }
throw new Error('No archive source configured');
} }
public async exportToTarGzStream() { /**
const tarPackStream = await this.tarTools.getPackStream(); * Get archive as a Buffer
const gzipStream = await this.gzipTools.getCompressionStream(); */
// const archiveStream = tarPackStream.pipe(gzipStream); public async toBuffer(): Promise<Buffer> {
// return archiveStream; if (this.archiveBuffer) {
return this.archiveBuffer;
}
const stream = await this.toStream();
return SmartArchive.streamToBuffer(stream);
} }
public async exportToFs(targetDir: string, fileNameArg?: string): Promise<void> { /**
* Write archive to a file
*/
public async toFile(filePath: string): Promise<void> {
const buffer = await this.toBuffer();
await plugins.fsPromises.mkdir(plugins.path.dirname(filePath), { recursive: true });
await plugins.fsPromises.writeFile(filePath, buffer);
}
/**
* Extract archive to filesystem
*/
public async extractToDirectory(
targetDir: string,
options?: Partial<IArchiveExtractionOptions>
): Promise<void> {
const done = plugins.smartpromise.defer<void>(); const done = plugins.smartpromise.defer<void>();
const streamFileStream = await this.exportToStreamOfStreamFiles(); const streamFileStream = await this.extractToStream();
streamFileStream.pipe(new plugins.smartstream.SmartDuplex({
streamFileStream.pipe(
new plugins.smartstream.SmartDuplex({
objectMode: true, objectMode: true,
writeFunction: async (chunkArg: plugins.smartfile.StreamFile, streamtools) => { writeFunction: async (streamFileArg: plugins.smartfile.StreamFile) => {
const done = plugins.smartpromise.defer<void>(); const innerDone = plugins.smartpromise.defer<void>();
console.log(chunkArg.relativeFilePath ? chunkArg.relativeFilePath : 'no relative path'); const streamFile = streamFileArg;
const streamFile = chunkArg; let relativePath = streamFile.relativeFilePath || options?.fileName || 'extracted_file';
// Apply stripComponents if specified
if (options?.stripComponents && options.stripComponents > 0) {
const parts = relativePath.split('/');
relativePath = parts.slice(options.stripComponents).join('/');
if (!relativePath) {
innerDone.resolve();
return;
}
}
// Apply filter if specified
if (options?.filter) {
const entryInfo: IArchiveEntryInfo = {
path: relativePath,
size: 0,
isDirectory: false,
isFile: true,
};
if (!options.filter(entryInfo)) {
innerDone.resolve();
return;
}
}
const readStream = await streamFile.createReadStream(); const readStream = await streamFile.createReadStream();
await plugins.smartfile.fs.ensureDir(targetDir); await plugins.fsPromises.mkdir(targetDir, { recursive: true });
const writePath = plugins.path.join(targetDir, (streamFile.relativeFilePath || fileNameArg)); const writePath = plugins.path.join(targetDir, relativePath);
await plugins.smartfile.fs.ensureDir(plugins.path.dirname(writePath)); await plugins.fsPromises.mkdir(plugins.path.dirname(writePath), { recursive: true });
const writeStream = plugins.smartfile.fsStream.createWriteStream(writePath); const writeStream = plugins.fs.createWriteStream(writePath);
readStream.pipe(writeStream); readStream.pipe(writeStream);
writeStream.on('finish', () => { writeStream.on('finish', () => {
done.resolve(); innerDone.resolve();
}) });
await done.promise; await innerDone.promise;
}, },
finalFunction: async () => { finalFunction: async () => {
done.resolve(); done.resolve();
} },
})); })
);
return done.promise; return done.promise;
} }
public async exportToStreamOfStreamFiles() { /**
* Extract archive to a stream of StreamFile objects
*/
public async extractToStream(): Promise<plugins.smartstream.StreamIntake<plugins.smartfile.StreamFile>> {
const streamFileIntake = new plugins.smartstream.StreamIntake<plugins.smartfile.StreamFile>({ const streamFileIntake = new plugins.smartstream.StreamIntake<plugins.smartfile.StreamFile>({
objectMode: true, objectMode: true,
}); });
const archiveStream = await this.getArchiveStream();
// Guard to prevent multiple signalEnd calls
let hasSignaledEnd = false;
const safeSignalEnd = () => {
if (!hasSignaledEnd) {
hasSignaledEnd = true;
streamFileIntake.signalEnd();
}
};
const archiveStream = await this.toStream();
const createAnalyzedStream = () => this.archiveAnalyzer.getAnalyzedStream(); const createAnalyzedStream = () => this.archiveAnalyzer.getAnalyzedStream();
// lets create a function that can be called multiple times to unpack layers of archives
const createUnpackStream = () => const createUnpackStream = () =>
plugins.smartstream.createTransformFunction<IAnalyzedResult, any>( plugins.smartstream.createTransformFunction<IAnalyzedResult, void>(
async (analyzedResultChunk) => { async (analyzedResultChunk) => {
if (analyzedResultChunk.fileType?.mime === 'application/x-tar') { if (analyzedResultChunk.fileType?.mime === 'application/x-tar') {
const tarStream = analyzedResultChunk.decompressionStream as plugins.tarStream.Extract; const tarStream = analyzedResultChunk.decompressionStream as plugins.tarStream.Extract;
tarStream.on(
'entry', tarStream.on('entry', async (header, stream, next) => {
async (header, stream, next) => { if (header.type === 'directory') {
const streamfile = plugins.smartfile.StreamFile.fromStream(stream, header.name); stream.resume();
streamFileIntake.push(streamfile); stream.on('end', () => next());
stream.on('end', function () { return;
next(); // ready for next entry
});
} }
);
tarStream.on('finish', function () { const passThrough = new plugins.stream.PassThrough();
console.log('finished'); const streamfile = plugins.smartfile.StreamFile.fromStream(passThrough, header.name);
streamFileIntake.signalEnd(); streamFileIntake.push(streamfile);
stream.pipe(passThrough);
stream.on('end', () => {
passThrough.end();
next();
}); });
});
tarStream.on('finish', () => {
safeSignalEnd();
});
analyzedResultChunk.resultStream.pipe(analyzedResultChunk.decompressionStream); analyzedResultChunk.resultStream.pipe(analyzedResultChunk.decompressionStream);
} else if (analyzedResultChunk.fileType?.mime === 'application/zip') {
analyzedResultChunk.resultStream
.pipe(analyzedResultChunk.decompressionStream)
.pipe(
new plugins.smartstream.SmartDuplex({
objectMode: true,
writeFunction: async (streamFileArg: plugins.smartfile.StreamFile) => {
streamFileIntake.push(streamFileArg);
},
finalFunction: async () => {
safeSignalEnd();
},
})
);
} else if (analyzedResultChunk.isArchive && analyzedResultChunk.decompressionStream) { } else if (analyzedResultChunk.isArchive && analyzedResultChunk.decompressionStream) {
// For nested archives (like gzip containing tar)
analyzedResultChunk.resultStream analyzedResultChunk.resultStream
.pipe(analyzedResultChunk.decompressionStream) .pipe(analyzedResultChunk.decompressionStream)
.pipe(createAnalyzedStream()) .pipe(createAnalyzedStream())
@@ -140,14 +434,156 @@ export class SmartArchive {
analyzedResultChunk.fileType?.ext analyzedResultChunk.fileType?.ext
); );
streamFileIntake.push(streamFile); streamFileIntake.push(streamFile);
streamFileIntake.signalEnd(); safeSignalEnd();
}
}, {
objectMode: true
} }
},
{ objectMode: true }
); );
archiveStream.pipe(createAnalyzedStream()).pipe(createUnpackStream()); archiveStream.pipe(createAnalyzedStream()).pipe(createUnpackStream());
return streamFileIntake; return streamFileIntake;
} }
/**
* Extract archive to an array of SmartFile objects (in-memory)
*/
public async extractToSmartFiles(): Promise<plugins.smartfile.SmartFile[]> {
const streamFiles = await this.extractToStream();
const smartFiles: plugins.smartfile.SmartFile[] = [];
return new Promise((resolve, reject) => {
streamFiles.on('data', async (streamFile: plugins.smartfile.StreamFile) => {
try {
const smartFile = await streamFile.toSmartFile();
smartFiles.push(smartFile);
} catch (err) {
reject(err);
}
});
streamFiles.on('end', () => resolve(smartFiles));
streamFiles.on('error', reject);
});
}
/**
* Extract a single file from the archive by path
*/
public async extractFile(filePath: string): Promise<plugins.smartfile.SmartFile | null> {
const streamFiles = await this.extractToStream();
return new Promise((resolve, reject) => {
let found = false;
streamFiles.on('data', async (streamFile: plugins.smartfile.StreamFile) => {
if (streamFile.relativeFilePath === filePath || streamFile.relativeFilePath?.endsWith(filePath)) {
found = true;
try {
const smartFile = await streamFile.toSmartFile();
resolve(smartFile);
} catch (err) {
reject(err);
}
}
});
streamFiles.on('end', () => {
if (!found) {
resolve(null);
}
});
streamFiles.on('error', reject);
});
}
// ============================================
// ANALYSIS METHODS
// ============================================
/**
* Analyze the archive and return metadata
*/
public async analyze(): Promise<IArchiveInfo> {
const stream = await this.toStream();
const firstChunk = await this.readFirstChunk(stream);
const fileType = await plugins.fileType.fileTypeFromBuffer(firstChunk);
let format: TArchiveFormat | null = null;
let isCompressed = false;
let isArchive = false;
if (fileType) {
switch (fileType.mime) {
case 'application/gzip':
format = 'gz';
isCompressed = true;
isArchive = true;
break;
case 'application/zip':
format = 'zip';
isCompressed = true;
isArchive = true;
break;
case 'application/x-tar':
format = 'tar';
isArchive = true;
break;
case 'application/x-bzip2':
format = 'bz2';
isCompressed = true;
isArchive = true;
break;
}
}
return {
format,
isCompressed,
isArchive,
};
}
/**
* List all entries in the archive without extracting
*/
public async listEntries(): Promise<IArchiveEntryInfo[]> {
const entries: IArchiveEntryInfo[] = [];
const streamFiles = await this.extractToStream();
return new Promise((resolve, reject) => {
streamFiles.on('data', (streamFile: plugins.smartfile.StreamFile) => {
entries.push({
path: streamFile.relativeFilePath || 'unknown',
size: 0, // Size not available without reading
isDirectory: false,
isFile: true,
});
});
streamFiles.on('end', () => resolve(entries));
streamFiles.on('error', reject);
});
}
/**
* Check if a specific file exists in the archive
*/
public async hasFile(filePath: string): Promise<boolean> {
const entries = await this.listEntries();
return entries.some((e) => e.path === filePath || e.path.endsWith(filePath));
}
/**
* Helper to read first chunk from stream
*/
private async readFirstChunk(stream: plugins.stream.Readable): Promise<Buffer> {
return new Promise((resolve, reject) => {
const onData = (chunk: Buffer) => {
stream.removeListener('data', onData);
stream.removeListener('error', reject);
resolve(chunk);
};
stream.on('data', onData);
stream.on('error', reject);
});
}
} }

View File

@@ -1,36 +1,208 @@
import type { SmartArchive } from './classes.smartarchive.js';
import * as plugins from './plugins.js'; import * as plugins from './plugins.js';
import type { IArchiveEntry, TCompressionLevel } from './interfaces.js';
import { GzipTools } from './classes.gziptools.js';
/**
* TAR archive creation and extraction utilities
*/
export class TarTools { export class TarTools {
smartArchiveRef: SmartArchive; /**
* Add a file to a TAR pack stream
*/
public async addFileToPack(
pack: plugins.tarStream.Pack,
optionsArg: {
fileName?: string;
content?:
| string
| Buffer
| plugins.stream.Readable
| plugins.smartfile.SmartFile
| plugins.smartfile.StreamFile;
byteLength?: number;
filePath?: string;
}
): Promise<void> {
return new Promise<void>(async (resolve, reject) => {
let fileName: string | null = null;
constructor(smartArchiveRefArg: SmartArchive) { if (optionsArg.fileName) {
this.smartArchiveRef = smartArchiveRefArg; fileName = optionsArg.fileName;
} else if (optionsArg.content instanceof plugins.smartfile.SmartFile) {
fileName = optionsArg.content.relative;
} else if (optionsArg.content instanceof plugins.smartfile.StreamFile) {
fileName = optionsArg.content.relativeFilePath;
} else if (optionsArg.filePath) {
fileName = optionsArg.filePath;
} }
// packing if (!fileName) {
public addFileToPack(pack: plugins.tarStream.Pack, fileName: string, content: string | Buffer) { reject(new Error('No filename specified for TAR entry'));
return new Promise<void>((resolve, reject) => { return;
const entry = pack.entry({ name: fileName, size: content.length }, (err: Error) => { }
// Determine content byte length
let contentByteLength: number | undefined;
if (optionsArg.byteLength) {
contentByteLength = optionsArg.byteLength;
} else if (typeof optionsArg.content === 'string') {
contentByteLength = Buffer.byteLength(optionsArg.content, 'utf8');
} else if (Buffer.isBuffer(optionsArg.content)) {
contentByteLength = optionsArg.content.length;
} else if (optionsArg.content instanceof plugins.smartfile.SmartFile) {
contentByteLength = await optionsArg.content.getSize();
} else if (optionsArg.content instanceof plugins.smartfile.StreamFile) {
contentByteLength = await optionsArg.content.getSize();
} else if (optionsArg.filePath) {
const fileStat = await plugins.fsPromises.stat(optionsArg.filePath);
contentByteLength = fileStat.size;
}
// Convert all content types to Readable stream
let content: plugins.stream.Readable;
if (Buffer.isBuffer(optionsArg.content)) {
content = plugins.stream.Readable.from(optionsArg.content);
} else if (typeof optionsArg.content === 'string') {
content = plugins.stream.Readable.from(Buffer.from(optionsArg.content));
} else if (optionsArg.content instanceof plugins.smartfile.SmartFile) {
content = plugins.stream.Readable.from(optionsArg.content.contents);
} else if (optionsArg.content instanceof plugins.smartfile.StreamFile) {
content = await optionsArg.content.createReadStream();
} else if (optionsArg.content instanceof plugins.stream.Readable) {
content = optionsArg.content;
} else if (optionsArg.filePath) {
content = plugins.fs.createReadStream(optionsArg.filePath);
} else {
reject(new Error('No content or filePath specified for TAR entry'));
return;
}
const entry = pack.entry(
{
name: fileName,
...(contentByteLength !== undefined ? { size: contentByteLength } : {}),
},
(err: Error | null) => {
if (err) { if (err) {
reject(err); reject(err);
} else { } else {
resolve(); resolve();
} }
}); }
);
entry.write(content); content.pipe(entry);
entry.end(); // Note: resolve() is called in the callback above when pipe completes
});
}
/**
* Pack a directory into a TAR stream
*/
public async packDirectory(directoryPath: string): Promise<plugins.tarStream.Pack> {
const fileTree = await plugins.listFileTree(directoryPath, '**/*');
const pack = await this.getPackStream();
for (const filePath of fileTree) {
const absolutePath = plugins.path.join(directoryPath, filePath);
const fileStat = await plugins.fsPromises.stat(absolutePath);
await this.addFileToPack(pack, {
byteLength: fileStat.size,
filePath: absolutePath,
fileName: filePath,
content: plugins.fs.createReadStream(absolutePath),
}); });
} }
public async getPackStream() {
const pack = plugins.tarStream.pack();
return pack; return pack;
} }
// extracting /**
getDecompressionStream() { * Get a new TAR pack stream
*/
public async getPackStream(): Promise<plugins.tarStream.Pack> {
return plugins.tarStream.pack();
}
/**
* Get a TAR extraction stream
*/
public getDecompressionStream(): plugins.tarStream.Extract {
return plugins.tarStream.extract(); return plugins.tarStream.extract();
} }
/**
* Pack files into a TAR buffer
*/
public async packFiles(files: IArchiveEntry[]): Promise<Buffer> {
const pack = await this.getPackStream();
for (const file of files) {
await this.addFileToPack(pack, {
fileName: file.archivePath,
content: file.content as string | Buffer | plugins.stream.Readable | plugins.smartfile.SmartFile | plugins.smartfile.StreamFile,
byteLength: file.size,
});
}
pack.finalize();
const chunks: Buffer[] = [];
return new Promise((resolve, reject) => {
pack.on('data', (chunk: Buffer) => chunks.push(chunk));
pack.on('end', () => resolve(Buffer.concat(chunks)));
pack.on('error', reject);
});
}
/**
* Pack a directory into a TAR.GZ buffer
*/
public async packDirectoryToTarGz(
directoryPath: string,
compressionLevel?: TCompressionLevel
): Promise<Buffer> {
const pack = await this.packDirectory(directoryPath);
pack.finalize();
const gzipTools = new GzipTools();
const gzipStream = gzipTools.getCompressionStream(compressionLevel);
const chunks: Buffer[] = [];
return new Promise((resolve, reject) => {
pack
.pipe(gzipStream)
.on('data', (chunk: Buffer) => chunks.push(chunk))
.on('end', () => resolve(Buffer.concat(chunks)))
.on('error', reject);
});
}
/**
* Pack a directory into a TAR.GZ stream
*/
public async packDirectoryToTarGzStream(
directoryPath: string,
compressionLevel?: TCompressionLevel
): Promise<plugins.stream.Readable> {
const pack = await this.packDirectory(directoryPath);
pack.finalize();
const gzipTools = new GzipTools();
const gzipStream = gzipTools.getCompressionStream(compressionLevel);
return pack.pipe(gzipStream);
}
/**
* Pack files into a TAR.GZ buffer
*/
public async packFilesToTarGz(
files: IArchiveEntry[],
compressionLevel?: TCompressionLevel
): Promise<Buffer> {
const tarBuffer = await this.packFiles(files);
const gzipTools = new GzipTools();
return gzipTools.compress(tarBuffer, compressionLevel);
}
} }

209
ts/classes.ziptools.ts Normal file
View File

@@ -0,0 +1,209 @@
import * as plugins from './plugins.js';
import type { IArchiveEntry, TCompressionLevel } from './interfaces.js';
/**
* Transform stream for ZIP decompression using fflate
* Emits StreamFile objects for each file in the archive
*/
export class ZipDecompressionTransform extends plugins.smartstream.SmartDuplex<Buffer, plugins.smartfile.StreamFile> {
private streamtools!: plugins.smartstream.IStreamTools;
private unzipper = new plugins.fflate.Unzip(async (fileArg) => {
let resultBuffer: Buffer;
fileArg.ondata = async (_flateError, dat, final) => {
resultBuffer
? (resultBuffer = Buffer.concat([resultBuffer, Buffer.from(dat)]))
: (resultBuffer = Buffer.from(dat));
if (final) {
const streamFile = plugins.smartfile.StreamFile.fromBuffer(resultBuffer);
streamFile.relativeFilePath = fileArg.name;
this.streamtools.push(streamFile);
}
};
fileArg.start();
});
constructor() {
super({
objectMode: true,
writeFunction: async (chunkArg, streamtoolsArg) => {
this.streamtools ? null : (this.streamtools = streamtoolsArg);
this.unzipper.push(
Buffer.isBuffer(chunkArg) ? chunkArg : Buffer.from(chunkArg as unknown as ArrayBuffer),
false
);
return null;
},
finalFunction: async () => {
this.unzipper.push(Buffer.from(''), true);
await plugins.smartdelay.delayFor(0);
await this.streamtools.push(null);
return null;
},
});
this.unzipper.register(plugins.fflate.UnzipInflate);
}
}
/**
* Streaming ZIP compression using fflate
* Allows adding multiple entries before finalizing
*/
export class ZipCompressionStream extends plugins.stream.Duplex {
private files: Map<string, { data: Uint8Array; options?: plugins.fflate.ZipOptions }> = new Map();
private finalized = false;
constructor() {
super();
}
/**
* Add a file entry to the ZIP archive
*/
public async addEntry(
fileName: string,
content: Buffer | plugins.stream.Readable,
options?: { compressionLevel?: TCompressionLevel }
): Promise<void> {
if (this.finalized) {
throw new Error('Cannot add entries to a finalized ZIP archive');
}
let data: Buffer;
if (Buffer.isBuffer(content)) {
data = content;
} else {
// Collect stream to buffer
const chunks: Buffer[] = [];
for await (const chunk of content) {
chunks.push(Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk));
}
data = Buffer.concat(chunks);
}
this.files.set(fileName, {
data: new Uint8Array(data),
options: options?.compressionLevel !== undefined ? { level: options.compressionLevel } : undefined,
});
}
/**
* Finalize the ZIP archive and emit the compressed data
*/
public async finalize(): Promise<void> {
if (this.finalized) {
return;
}
this.finalized = true;
const filesObj: plugins.fflate.Zippable = {};
for (const [name, { data, options }] of this.files) {
filesObj[name] = options ? [data, options] : data;
}
return new Promise((resolve, reject) => {
plugins.fflate.zip(filesObj, (err, result) => {
if (err) {
reject(err);
} else {
this.push(Buffer.from(result));
this.push(null);
resolve();
}
});
});
}
_read(): void {
// No-op: data is pushed when finalize() is called
}
_write(
_chunk: Buffer,
_encoding: BufferEncoding,
callback: (error?: Error | null) => void
): void {
// Not used for ZIP creation - use addEntry() instead
callback(new Error('Use addEntry() to add files to the ZIP archive'));
}
}
/**
* ZIP compression and decompression utilities
*/
export class ZipTools {
/**
* Get a streaming compression object for creating ZIP archives
*/
public getCompressionStream(): ZipCompressionStream {
return new ZipCompressionStream();
}
/**
* Get a streaming decompression transform for extracting ZIP archives
*/
public getDecompressionStream(): ZipDecompressionTransform {
return new ZipDecompressionTransform();
}
/**
* Create a ZIP archive from an array of entries
*/
public async createZip(entries: IArchiveEntry[], compressionLevel?: TCompressionLevel): Promise<Buffer> {
const filesObj: plugins.fflate.Zippable = {};
for (const entry of entries) {
let data: Uint8Array;
if (typeof entry.content === 'string') {
data = new TextEncoder().encode(entry.content);
} else if (Buffer.isBuffer(entry.content)) {
data = new Uint8Array(entry.content);
} else if (entry.content instanceof plugins.smartfile.SmartFile) {
data = new Uint8Array(entry.content.contents);
} else if (entry.content instanceof plugins.smartfile.StreamFile) {
const buffer = await entry.content.getContentAsBuffer();
data = new Uint8Array(buffer);
} else {
// Readable stream
const chunks: Buffer[] = [];
for await (const chunk of entry.content as plugins.stream.Readable) {
chunks.push(Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk));
}
data = new Uint8Array(Buffer.concat(chunks));
}
if (compressionLevel !== undefined) {
filesObj[entry.archivePath] = [data, { level: compressionLevel }];
} else {
filesObj[entry.archivePath] = data;
}
}
return new Promise((resolve, reject) => {
plugins.fflate.zip(filesObj, (err, result) => {
if (err) reject(err);
else resolve(Buffer.from(result));
});
});
}
/**
* Extract a ZIP buffer to an array of entries
*/
public async extractZip(data: Buffer): Promise<Array<{ path: string; content: Buffer }>> {
return new Promise((resolve, reject) => {
plugins.fflate.unzip(data, (err, result) => {
if (err) {
reject(err);
return;
}
const entries: Array<{ path: string; content: Buffer }> = [];
for (const [path, content] of Object.entries(result)) {
entries.push({ path, content: Buffer.from(content) });
}
resolve(entries);
});
});
}
}

70
ts/errors.ts Normal file
View File

@@ -0,0 +1,70 @@
/**
* Base error class for smartarchive
*/
export class SmartArchiveError extends Error {
public readonly code: string;
constructor(message: string, code: string) {
super(message);
this.name = 'SmartArchiveError';
this.code = code;
// Maintains proper stack trace for where error was thrown (V8)
if (Error.captureStackTrace) {
Error.captureStackTrace(this, this.constructor);
}
}
}
/**
* BZIP2-specific decompression errors
*/
export class Bzip2Error extends SmartArchiveError {
constructor(message: string, code: string = 'BZIP2_ERROR') {
super(message, code);
this.name = 'Bzip2Error';
}
}
/**
* Archive format detection errors
*/
export class ArchiveFormatError extends SmartArchiveError {
constructor(message: string) {
super(message, 'ARCHIVE_FORMAT_ERROR');
this.name = 'ArchiveFormatError';
}
}
/**
* Stream processing errors
*/
export class StreamError extends SmartArchiveError {
constructor(message: string) {
super(message, 'STREAM_ERROR');
this.name = 'StreamError';
}
}
/**
* BZIP2 error codes for programmatic error handling
*/
export const BZIP2_ERROR_CODES = {
NO_MAGIC_NUMBER: 'BZIP2_NO_MAGIC',
INVALID_ARCHIVE: 'BZIP2_INVALID_ARCHIVE',
CRC_MISMATCH: 'BZIP2_CRC_MISMATCH',
INVALID_BLOCK_DATA: 'BZIP2_INVALID_BLOCK',
BUFFER_OVERFLOW: 'BZIP2_BUFFER_OVERFLOW',
INVALID_HUFFMAN: 'BZIP2_INVALID_HUFFMAN',
INVALID_SELECTOR: 'BZIP2_INVALID_SELECTOR',
INVALID_POSITION: 'BZIP2_INVALID_POSITION',
PREMATURE_END: 'BZIP2_PREMATURE_END',
} as const;
export type TBzip2ErrorCode = typeof BZIP2_ERROR_CODES[keyof typeof BZIP2_ERROR_CODES];
/**
* Throw a BZIP2 error with a specific code
*/
export function throwBzip2Error(message: string, code: TBzip2ErrorCode): never {
throw new Bzip2Error(message, code);
}

View File

@@ -1 +1,15 @@
// Core types and errors
export * from './interfaces.js';
export * from './errors.js';
// Main archive class
export * from './classes.smartarchive.js'; export * from './classes.smartarchive.js';
// Format-specific tools
export * from './classes.tartools.js';
export * from './classes.ziptools.js';
export * from './classes.gziptools.js';
export * from './classes.bzip2tools.js';
// Archive analysis
export * from './classes.archiveanalyzer.js';

131
ts/interfaces.ts Normal file
View File

@@ -0,0 +1,131 @@
import type * as stream from 'node:stream';
import type { SmartFile, StreamFile } from '@push.rocks/smartfile';
/**
* Supported archive formats
*/
export type TArchiveFormat = 'tar' | 'tar.gz' | 'tgz' | 'zip' | 'gz' | 'bz2';
/**
* Compression level (0 = no compression, 9 = maximum compression)
*/
export type TCompressionLevel = 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9;
/**
* Supported MIME types for archive detection
*/
export type TSupportedMime =
| 'application/gzip'
| 'application/zip'
| 'application/x-bzip2'
| 'application/x-tar'
| undefined;
/**
* Entry to add to an archive during creation
*/
export interface IArchiveEntry {
/** Path within the archive */
archivePath: string;
/** Content: string, Buffer, Readable stream, SmartFile, or StreamFile */
content: string | Buffer | stream.Readable | SmartFile | StreamFile;
/** Optional size hint for streams (improves performance) */
size?: number;
/** Optional file mode/permissions */
mode?: number;
/** Optional modification time */
mtime?: Date;
}
/**
* Options for creating archives
*/
export interface IArchiveCreationOptions {
/** Target archive format */
format: TArchiveFormat;
/** Compression level (0-9, default depends on format) */
compressionLevel?: TCompressionLevel;
/** Base path to strip from file paths in archive */
basePath?: string;
}
/**
* Options for extracting archives
*/
export interface IArchiveExtractionOptions {
/** Target directory for extraction */
targetDir: string;
/** Optional filename for single-file archives (gz, bz2) */
fileName?: string;
/** Number of leading path components to strip */
stripComponents?: number;
/** Filter function to select which entries to extract */
filter?: (entry: IArchiveEntryInfo) => boolean;
/** Whether to overwrite existing files */
overwrite?: boolean;
}
/**
* Information about an archive entry
*/
export interface IArchiveEntryInfo {
/** Path of the entry within the archive */
path: string;
/** Size in bytes */
size: number;
/** Whether this entry is a directory */
isDirectory: boolean;
/** Whether this entry is a file */
isFile: boolean;
/** Modification time */
mtime?: Date;
/** File mode/permissions */
mode?: number;
}
/**
* Result of archive analysis
*/
export interface IArchiveInfo {
/** Detected archive format */
format: TArchiveFormat | null;
/** Whether the archive is compressed */
isCompressed: boolean;
/** Whether this is a recognized archive format */
isArchive: boolean;
/** List of entries (if available without full extraction) */
entries?: IArchiveEntryInfo[];
}
/**
* Options for adding a file to a TAR pack stream
*/
export interface IAddFileOptions {
/** Filename within the archive */
fileName?: string;
/** File content */
content?: string | Buffer | stream.Readable | SmartFile | StreamFile;
/** Size in bytes (required for streams) */
byteLength?: number;
/** Path to file on disk (alternative to content) */
filePath?: string;
}
/**
* Bit reader interface for BZIP2 decompression
*/
export interface IBitReader {
(n: number | null): number | void;
bytesRead: number;
}
/**
* Huffman group for BZIP2 decompression
*/
export interface IHuffmanGroup {
permute: Int32Array;
limit: Int32Array;
base: Int32Array;
minLen: number;
maxLen: number;
}

View File

@@ -2,6 +2,6 @@ import * as plugins from './plugins.js';
export const packageDir = plugins.path.join( export const packageDir = plugins.path.join(
plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url), plugins.smartpath.get.dirnameFromImportMetaUrl(import.meta.url),
'../' '../',
); );
export const nogitDir = plugins.path.join(packageDir, './.nogit'); export const nogitDir = plugins.path.join(packageDir, './.nogit');

View File

@@ -1,11 +1,38 @@
// node native scope // node native scope
import * as path from 'path'; import * as path from 'node:path';
import * as stream from 'stream'; import * as stream from 'node:stream';
import * as fs from 'node:fs';
import * as fsPromises from 'node:fs/promises';
export { path, stream }; export { path, stream, fs, fsPromises };
/**
* List files in a directory recursively, returning relative paths
*/
export async function listFileTree(dirPath: string, _pattern: string = '**/*'): Promise<string[]> {
const results: string[] = [];
async function walkDir(currentPath: string, relativePath: string = '') {
const entries = await fsPromises.readdir(currentPath, { withFileTypes: true });
for (const entry of entries) {
const entryRelPath = relativePath ? path.join(relativePath, entry.name) : entry.name;
const entryFullPath = path.join(currentPath, entry.name);
if (entry.isDirectory()) {
await walkDir(entryFullPath, entryRelPath);
} else if (entry.isFile()) {
results.push(entryRelPath);
}
}
}
await walkDir(dirPath);
return results;
}
// @pushrocks scope // @pushrocks scope
import * as smartfile from '@push.rocks/smartfile'; import * as smartfile from '@push.rocks/smartfile';
import * as smartdelay from '@push.rocks/smartdelay';
import * as smartpath from '@push.rocks/smartpath'; import * as smartpath from '@push.rocks/smartpath';
import * as smartpromise from '@push.rocks/smartpromise'; import * as smartpromise from '@push.rocks/smartpromise';
import * as smartrequest from '@push.rocks/smartrequest'; import * as smartrequest from '@push.rocks/smartrequest';
@@ -14,7 +41,17 @@ import * as smartstream from '@push.rocks/smartstream';
import * as smartrx from '@push.rocks/smartrx'; import * as smartrx from '@push.rocks/smartrx';
import * as smarturl from '@push.rocks/smarturl'; import * as smarturl from '@push.rocks/smarturl';
export { smartfile, smartpath, smartpromise, smartrequest, smartunique, smartstream, smartrx, smarturl }; export {
smartfile,
smartdelay,
smartpath,
smartpromise,
smartrequest,
smartunique,
smartstream,
smartrx,
smarturl,
};
// third party scope // third party scope
import * as fileType from 'file-type'; import * as fileType from 'file-type';

View File

@@ -6,9 +6,9 @@
"module": "NodeNext", "module": "NodeNext",
"moduleResolution": "NodeNext", "moduleResolution": "NodeNext",
"esModuleInterop": true, "esModuleInterop": true,
"verbatimModuleSyntax": true "verbatimModuleSyntax": true,
"baseUrl": ".",
"paths": {}
}, },
"exclude": [ "exclude": ["dist_*/**/*.d.ts"]
"dist_*/**/*.d.ts"
]
} }