dartboard-ia 0.2.1__tar.gz

dartboard_ia-0.2.1/LICENSE

@@ -0,0 +1,121 @@
+Creative Commons Legal Code
+
+CC0 1.0 Universal
+
+    CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
+    LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
+    ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
+    INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
+    REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
+    PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
+    THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
+    HEREUNDER.
+
+Statement of Purpose
+
+The laws of most jurisdictions throughout the world automatically confer
+exclusive Copyright and Related Rights (defined below) upon the creator
+and subsequent owner(s) (each and all, an "owner") of an original work of
+authorship and/or a database (each, a "Work").
+
+Certain owners wish to permanently relinquish those rights to a Work for
+the purpose of contributing to a commons of creative, cultural and
+scientific works ("Commons") that the public can reliably and without fear
+of later claims of infringement build upon, modify, incorporate in other
+works, reuse and redistribute as freely as possible in any form whatsoever
+and for any purposes, including without limitation commercial purposes.
+These owners may contribute to the Commons to promote the ideal of a free
+culture and the further production of creative, cultural and scientific
+works, or to gain reputation or greater distribution for their Work in
+part through the use and efforts of others.
+
+For these and/or other purposes and motivations, and without any
+expectation of additional consideration or compensation, the person
+associating CC0 with a Work (the "Affirmer"), to the extent that he or she
+is an owner of Copyright and Related Rights in the Work, voluntarily
+elects to apply CC0 to the Work and publicly distribute the Work under its
+terms, with knowledge of his or her Copyright and Related Rights in the
+Work and the meaning and intended legal effect of CC0 on those rights.
+
+1. Copyright and Related Rights. A Work made available under CC0 may be
+protected by copyright and related or neighboring rights ("Copyright and
+Related Rights"). Copyright and Related Rights include, but are not
+limited to, the following:
+
+  i. the right to reproduce, adapt, distribute, perform, display,
+     communicate, and translate a Work;
+ ii. moral rights retained by the original author(s) and/or performer(s);
+iii. publicity and privacy rights pertaining to a person's image or
+     likeness depicted in a Work;
+ iv. rights protecting against unfair competition in regards to a Work,
+     subject to the limitations in paragraph 4(a), below;
+  v. rights protecting the extraction, dissemination, use and reuse of data
+     in a Work;
+ vi. database rights (such as those arising under Directive 96/9/EC of the
+     European Parliament and of the Council of 11 March 1996 on the legal
+     protection of databases, and under any national implementation
+     thereof, including any amended or successor version of such
+     directive); and
+vii. other similar, equivalent or corresponding rights throughout the
+     world based on applicable law or treaty, and any national
+     implementations thereof.
+
+2. Waiver. To the greatest extent permitted by, but not in contravention
+of, applicable law, Affirmer hereby overtly, fully, permanently,
+irrevocably and unconditionally waives, abandons, and surrenders all of
+Affirmer's Copyright and Related Rights and associated claims and causes
+of action, whether now known or unknown (including existing as well as
+future claims and causes of action), in the Work (i) in all territories
+worldwide, (ii) for the maximum duration provided by applicable law or
+treaty (including future time extensions), (iii) in any current or future
+medium and for any number of copies, and (iv) for any purpose whatsoever,
+including without limitation commercial, advertising or promotional
+purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
+member of the public at large and to the detriment of Affirmer's heirs and
+successors, fully intending that such Waiver shall not be subject to
+revocation, rescission, cancellation, termination, or any other legal or
+equitable action to disrupt the quiet enjoyment of the Work by the public
+as contemplated by Affirmer's express Statement of Purpose.
+
+3. Public License Fallback. Should any part of the Waiver for any reason
+be judged legally invalid or ineffective under applicable law, then the
+Waiver shall be preserved to the maximum extent permitted taking into
+account Affirmer's express Statement of Purpose. In addition, to the
+extent the Waiver is so judged Affirmer hereby grants to each affected
+person a royalty-free, non transferable, non sublicensable, non exclusive,
+irrevocable and unconditional license to exercise Affirmer's Copyright and
+Related Rights in the Work (i) in all territories worldwide, (ii) for the
+maximum duration provided by applicable law or treaty (including future
+time extensions), (iii) in any current or future medium and for any number
+of copies, and (iv) for any purpose whatsoever, including without
+limitation commercial, advertising or promotional purposes (the
+"License"). The License shall be deemed effective as of the date CC0 was
+applied by Affirmer to the Work. Should any part of the License for any
+reason be judged legally invalid or ineffective under applicable law, such
+partial invalidity or ineffectiveness shall not invalidate the remainder
+of the License, and in such case Affirmer hereby affirms that he or she
+will not (i) exercise any of his or her remaining Copyright and Related
+Rights in the Work or (ii) assert any associated claims and causes of
+action with respect to the Work, in either case contrary to Affirmer's
+express Statement of Purpose.
+
+4. Limitations and Disclaimers.
+
+ a. No trademark or patent rights held by Affirmer are waived, abandoned,
+    surrendered, licensed or otherwise affected by this document.
+ b. Affirmer offers the Work as-is and makes no representations or
+    warranties of any kind concerning the Work, express, implied,
+    statutory or otherwise, including without limitation warranties of
+    title, merchantability, fitness for a particular purpose, non
+    infringement, or the absence of latent or other defects, accuracy, or
+    the present or absence of errors, whether or not discoverable, all to
+    the greatest extent permissible under applicable law.
+ c. Affirmer disclaims responsibility for clearing rights of other persons
+    that may apply to the Work or any use thereof, including without
+    limitation any person's Copyright and Related Rights in the Work.
+    Further, Affirmer disclaims responsibility for obtaining any necessary
+    consents, permissions or other rights required for any use of the
+    Work.
+ d. Affirmer understands and acknowledges that Creative Commons is not a
+    party to this document and has no duty or obligation with respect to
+    this CC0 or use of the Work.

dartboard_ia-0.2.1/PKG-INFO

@@ -0,0 +1,59 @@
+Metadata-Version: 2.4
+Name: dartboard-ia
+Version: 0.2.1
+Summary: Internet Archive upload management tool
+License-File: LICENSE
+Author: DigitalDragon
+Requires-Python: >=3.8
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Dist: dataclasses-json
+Requires-Dist: internetarchive (>=5.0.3)
+Project-URL: Repository, https://github.com/DigitalDwagon/dartboard
+Description-Content-Type: text/markdown
+
+# dartboard
+generalized Internet Archive upload target
+
+## Configuration
+To use dartboard, you'll need a `config.json` in the same directory where you run it (or pass the location of it with `--config-path` in your dartboard command).
+```json
+{
+  "s3_key": "abcdefg",
+  "s3_secret": "abcdefg"
+}
+```
+
+## Usage instructions
+You can upload a directory with
+```bash
+dartboard path/to/directory
+```
+dartboard will try to upload to the item with the same identifier as the name of the directory. If the item does not exist, you must specify the metadata by placing an `__ia_meta.json` file in the directory:
+```json
+{
+  "collection": "opensource",
+  "mediatype": "data",
+  "title": "My title",
+  "description": "My description",
+  "foo": "bar"
+}
+```
+If the item already exists, dartboard will try to upload the files to it with or without `__ia_meta.json` being present. If it is present, dartboard WILL attempt to diff the metadata and make the necessary changes once it has finished uploading the new files.
+
+You can also specify dartboard settings for that item with an `__uploader_meta.json` file:
+```java
+{
+  "setUploadState": false, // if enabled, dartboard will set an upload-state:uploading key on the item, and change it to upload-state:uploaded when done
+  "setScanner": true, // if disabled, dartboard will not add "dartboard (vX.Y.Z)" to the scanner field
+  "sendSizeHint": false, // if enabled, dartboard will send IA a size hint for the item, based on the size of files in the directory
+  "derive": true // if disabled, dartboard will not queue a derive task once it has finished uploading
+}
+```
+

dartboard_ia-0.2.1/README.md

@@ -0,0 +1,38 @@
+# dartboard
+generalized Internet Archive upload target
+
+## Configuration
+To use dartboard, you'll need a `config.json` in the same directory where you run it (or pass the location of it with `--config-path` in your dartboard command).
+```json
+{
+  "s3_key": "abcdefg",
+  "s3_secret": "abcdefg"
+}
+```
+
+## Usage instructions
+You can upload a directory with
+```bash
+dartboard path/to/directory
+```
+dartboard will try to upload to the item with the same identifier as the name of the directory. If the item does not exist, you must specify the metadata by placing an `__ia_meta.json` file in the directory:
+```json
+{
+  "collection": "opensource",
+  "mediatype": "data",
+  "title": "My title",
+  "description": "My description",
+  "foo": "bar"
+}
+```
+If the item already exists, dartboard will try to upload the files to it with or without `__ia_meta.json` being present. If it is present, dartboard WILL attempt to diff the metadata and make the necessary changes once it has finished uploading the new files.
+
+You can also specify dartboard settings for that item with an `__uploader_meta.json` file:
+```java
+{
+  "setUploadState": false, // if enabled, dartboard will set an upload-state:uploading key on the item, and change it to upload-state:uploaded when done
+  "setScanner": true, // if disabled, dartboard will not add "dartboard (vX.Y.Z)" to the scanner field
+  "sendSizeHint": false, // if enabled, dartboard will send IA a size hint for the item, based on the size of files in the directory
+  "derive": true // if disabled, dartboard will not queue a derive task once it has finished uploading
+}
+```

dartboard_ia-0.2.1/dartboard/__version__.py

@@ -0,0 +1,3 @@
+import importlib.metadata
+
+version : str = importlib.metadata.version("dartboard-ia")

dartboard_ia-0.2.1/dartboard/config.py

@@ -0,0 +1,12 @@
+import dataclasses
+
+@dataclasses.dataclass
+class Config:
+    s3_key: str = ""
+    s3_secret: str = ""
+
+    staging_directory: str = "dartboard-staging"
+    working_directory: str = "dartboard-uploading"
+    done_directory: str = "dartboard-done"
+
+    dry_run: bool = False

dartboard_ia-0.2.1/dartboard/items.py

@@ -0,0 +1,13 @@
+import dataclasses
+
+import dataclasses_json
+from dataclasses_json import LetterCase, dataclass_json
+
+
+@dataclass_json(letter_case=LetterCase.CAMEL)
+@dataclasses.dataclass
+class UploaderMeta:
+    set_scanner : bool = True
+    set_upload_state: bool = False
+    send_size_hint: bool = False
+    derive: bool = True

dartboard_ia-0.2.1/dartboard/main.py

@@ -0,0 +1,40 @@
+import argparse
+import json
+import logging
+
+from dartboard.__version__ import version
+from dartboard.config import Config
+from dartboard.upload import upload
+
+def main():
+    logging.basicConfig(level=logging.INFO,
+                        format='%(asctime)s | %(message)s',
+                        datefmt='%Y-%m-%d %H:%M:%S')
+    logging.log(logging.INFO, "Dartboard is loading...")
+
+
+    parser = argparse.ArgumentParser(description=f"dartboard (v{version})")
+    parser.add_argument("--config-path", dest="config_path", type=str, default="config.json",
+                        help="Path to the config file (default: ./config.json)")
+    parser.add_argument("path", type=str, nargs="?", default=None,
+                        help="Path to the directory to upload")
+    parser.add_argument("--dry-run", dest="dry_run", action="store_true",
+                        help="Run the upload process without actually uploading anything")
+    args = parser.parse_args()
+
+    if args.path is None:
+        parser.print_help()
+        exit(1)
+
+    with open(args.config_path, "r") as config_file:
+        config_dict = json.loads(config_file.read().replace("\n", ""))
+
+    config = Config(**config_dict)
+    if args.dry_run:
+        config.dry_run = True
+
+    upload(config, args.path)
+
+
+if __name__ == "__main__":
+    main()

dartboard_ia-0.2.1/dartboard/upload.py

@@ -0,0 +1,236 @@
+import hashlib
+import json
+import logging
+import os.path
+import re
+import time
+
+import internetarchive
+from internetarchive import get_tasks, get_session, ArchiveSession
+
+from dartboard.config import Config
+from dartboard.items import UploaderMeta
+from dartboard.__version__ import version
+
+
+def upload(config: Config, path: str):
+    path = os.path.normpath(path)
+    logging.log(logging.INFO, f"Uploading {path}...")
+
+    identifier: str = get_identifier(path)
+    if not identifier:
+        return False
+    logging.log(logging.INFO, f"Identifier: {identifier} - this item will try to upload to https://archive.org/details/{identifier}")
+
+    session: ArchiveSession = get_session({"s3": {"access": config.s3_key, "secret": config.s3_secret}})
+    item = internetarchive.get_item(identifier, archive_session=session)
+    metadata = load_metadata(path)
+    settings = load_uploader_settings(path)
+
+    if not metadata and not item.exists:
+        logging.log(logging.ERROR, f"{identifier} does not exist and doesn't have a metadata file. Cannot upload.")
+        return False
+
+    if settings.set_scanner:
+        if "scanner" not in metadata or not metadata["scanner"]:
+            metadata["scanner"] = []
+        if isinstance(metadata["scanner"], str):
+            metadata["scanner"] = [metadata["scanner"]]
+        metadata["scanner"].append(f"dartboard (v{version})")
+
+    if settings.set_upload_state:
+        metadata["upload-state"] = "uploading"
+
+    logging.log(logging.INFO, f"Metadata: {json.dumps(metadata, indent=4)}")
+
+    files_to_upload: dict[str, str] = get_files_to_upload(path, item)
+
+    logging.log(logging.INFO, f"Found files:")
+    for filepath, destination in files_to_upload.items():
+        logging.log(logging.INFO, f"    {filepath} -> {destination}")
+
+    if not files_to_upload.items():
+        logging.log(logging.INFO, f"No files to upload!")
+        return True
+
+    uploaded_files: dict[str, str] = {}
+
+    for filepath, destination in files_to_upload.items():
+        headers = {}
+
+        if settings.send_size_hint and not uploaded_files:
+            headers["x-archive-size-hint"] = str(get_size(files_to_upload))
+
+        logging.log(logging.INFO, f"Uploading {filepath} to {identifier}...")
+        if config.dry_run:
+            logging.log(logging.INFO, f"Dry run - skipping upload")
+            continue
+        item.upload(files={destination: filepath},
+                    metadata=metadata,
+                    queue_derive=False,
+                    headers=headers,
+                    verbose=True,
+                    access_key=config.s3_key,
+                    secret_key=config.s3_secret
+                    )
+
+    # Final upload completions after all files are uploaded - update the metadata, run derives, etc
+    if config.dry_run:
+        logging.log(logging.INFO, f"Dry run - exiting early! Can't update metadata or derive an item that does not exist.")
+        return True
+
+    if not wait_for_item(identifier):
+        return False
+
+    if settings.set_upload_state:
+        metadata["upload-state"] = "uploaded"
+
+    item = internetarchive.get_item(identifier, archive_session=session)
+    metadata_changes = {}
+    item_metadata = item.metadata
+    # diff the metadata
+    # keys that are in metadata but not in item_metadata or keys that are present in both, but have different values
+    # ignore keys that are only in item_metadata
+    #print(item_metadata)
+    for key in metadata.keys():
+        if key == "description" and "<a" in metadata[key]:
+            # TODO: IA sanitizes description HTML (eg. with nofollow) so this will result in us always updating the description field...
+            # For now we just skip it
+            continue
+
+        if key not in item_metadata:
+            metadata_changes[key] = metadata[key]
+            continue
+
+        if isinstance(item_metadata[key], list) or isinstance(metadata[key], list):
+            item_value = item_metadata[key] if isinstance(item_metadata[key], list) else [item_metadata[key]]
+            metadata_value = metadata[key] if isinstance(metadata[key], list) else [metadata[key]]
+            value = list(set(item_value) | set(metadata_value))
+
+            if len(value) > len(item_value):
+                metadata_changes[key] = value
+            continue
+
+        if item_metadata[key] != metadata[key]:
+            metadata_changes[key] = metadata[key]
+
+
+    # if there are changes, update the metadata
+    if metadata_changes:
+        logging.log(logging.INFO, f"Updating metadata for {identifier}...")
+        logging.log(logging.INFO, f"Metadata changes: {json.dumps(metadata_changes, indent=4)}")
+        item.modify_metadata(metadata_changes)
+
+    if settings.derive:
+        # TODO: check that there is no queued/running derive task already
+        logging.log(logging.INFO, f"Deriving {identifier}...")
+        tasks = get_tasks(identifier, {"cmd":"derive.php", "history":"0"}, archive_session=session)
+        if tasks:
+            logging.log(logging.INFO, f"-> Found a derive task ({tasks.pop().task_id}) already running for {identifier} - see https://archive.org/history/{identifier}")
+        else:
+            ""
+            item.derive()
+
+    logging.log(logging.INFO, f"Success! Upload complete - {identifier} is now available at https://archive.org/details/{identifier}")
+
+    return True
+
+
+def get_size(files: dict[str, str]) -> int:
+    size = 0
+    for file in files:
+        size += os.path.getsize(file)
+    return size
+
+def get_files_to_upload(path: str, item: internetarchive.Item) -> dict[str, str]:
+    files: dict[str, str] = {}
+    for dirpath, dirnames, filenames in os.walk(path):
+        for f in filenames:
+            fp = os.path.join(dirpath, f)
+            # skip if it is symbolic link
+            if not os.path.islink(fp):
+                # get the relative path
+                rel_path = os.path.relpath(fp, path)
+                rel_path = rel_path.replace(os.path.sep, "/")
+                abs_path = os.path.abspath(fp)
+                files[abs_path] = rel_path
+
+    # remove __ia_meta.json and __uploader_meta.json from the list
+    for path, destination in list(files.items()):
+        if destination == "__ia_meta.json" or destination == "__uploader_meta.json":
+            files.pop(path, None)
+
+    if not item.exists:
+        return files
+
+    for path, destination in list(files.items()):
+        ia_file = next((file for file in item.files if file["name"] == destination), None)
+
+        if ia_file:
+            if ia_file["md5"] == hashlib.md5(open(path, "rb").read()).hexdigest():
+                logging.log(logging.INFO, f"{destination} already exists in {item.identifier}. Skipping...")
+                # remove the file from the list
+                files.pop(path, None)
+                continue
+            else:
+                raise Exception(f"{destination} already exists in {item.identifier}, but the hashes don't match.")
+
+    return files
+
+def get_identifier(path: str) -> str:
+    if not os.path.isdir(path):
+        logging.log(logging.ERROR, f"{path} is not a directory")
+        return None
+
+    identifier: str = os.path.basename(path)
+
+    if not identifier:
+        logging.log(logging.ERROR, f"{path} does not have an identifier")
+        return None
+
+    # identifier validity: https://archive.org/developers/metadata-schema/index.html#archive-org-identifiers
+    if not re.match(r"^[a-zA-Z0-9-_.]{5,100}$", identifier):
+        logging.log(logging.ERROR, f"{identifier} is not a valid identifier. Identifiers should be 5-100 characters long and can only contain letters, numbers, dashes, underscores, and periods.")
+        return None
+
+    return identifier
+
+def load_metadata(path: str) -> dict:
+    try:
+        with open(os.path.join(path, "__ia_meta.json"), "r") as meta_file:
+            metadata = meta_file.read()
+            if metadata:
+                return json.loads(metadata)
+            else:
+                return {}
+    except FileNotFoundError:
+        return {}
+
+def load_uploader_settings(path: str) -> UploaderMeta:
+    try:
+        with open(os.path.join(path, "__uploader_meta.json"), "r") as meta_file:
+            settings_raw = meta_file.read()
+            if settings_raw:
+                return UploaderMeta.from_json(settings_raw)
+            else:
+                return UploaderMeta()
+    except FileNotFoundError:
+        return UploaderMeta()
+
+def wait_for_item(identifier: str) -> bool:
+    # "borrowed" and modified from the wikiteam3 uploader
+    item = internetarchive.get_item(identifier)
+    tries = 400
+    for tries_left in range(tries, 0, -1):
+        if item.exists:
+            return True
+
+        logging.log(logging.INFO, msg=f"Waiting for the item to be created... ({tries_left} tries left)  ...")
+        if tries < 395:
+            logging.log(logging.INFO, msg=f"Is IA overloaded? Still waiting for item to be created ({tries_left} tries left)  ...")
+        time.sleep(30)
+        item = internetarchive.get_item(identifier)
+
+    if not item.exists:
+        logging.log(logging.ERROR, msg=f"IA overloaded, the item is still not ready after {400 * 30} seconds")
+        return False

dartboard_ia-0.2.1/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["poetry-core>=2.0.0,<3.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[project]
+name = "dartboard-ia"
+version = "0.2.1"
+authors = [
+    {name = "DigitalDragon"}
+]
+description = "Internet Archive upload management tool"
+readme = "README.md"
+requires-python = ">=3.8"
+dependencies = [
+    "internetarchive>=5.0.3",
+    "dataclasses-json"
+]
+
+[project.urls]
+repository = "https://github.com/DigitalDwagon/dartboard"
+
+[tool.poetry]
+packages = [
+    {include = "dartboard"}
+]
+
+[project.scripts]
+dartboard = "dartboard.main:main"
+