meshagent-commoncrawl 0.39.3__tar.gz

meshagent_commoncrawl-0.39.3/LICENSE

@@ -0,0 +1,201 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction,
+and distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by
+the copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all
+other entities that control, are controlled by, or are under common
+control with that entity. For the purposes of this definition,
+"control" means (i) the power, direct or indirect, to cause the
+direction or management of such entity, whether by contract or
+otherwise, or (ii) ownership of fifty percent (50%) or more of the
+outstanding shares, or (iii) beneficial ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity
+exercising permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation
+source, and configuration files.
+
+"Object" form shall mean any form resulting from mechanical
+transformation or translation of a Source form, including but
+not limited to compiled object code, generated documentation,
+and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or
+Object form, made available under the License, as indicated by a
+copyright notice that is included in or attached to the work
+(an example is provided in the Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object
+form, that is based on (or derived from) the Work and for which the
+editorial revisions, annotations, elaborations, or other modifications
+represent, as a whole, an original work of authorship. For the purposes
+of this License, Derivative Works shall not include works that remain
+separable from, or merely link (or bind by name) to the interfaces of,
+the Work and Derivative Works thereof.
+
+"Contribution" shall mean any work of authorship, including
+the original version of the Work and any modifications or additions
+to that Work or Derivative Works thereof, that is intentionally
+submitted to Licensor for inclusion in the Work by the copyright owner
+or by an individual or Legal Entity authorized to submit on behalf of
+the copyright owner. For the purposes of this definition, "submitted"
+means any form of electronic, verbal, or written communication sent
+to the Licensor or its representatives, including but not limited to
+communication on electronic mailing lists, source code control systems,
+and issue tracking systems that are managed by, or on behalf of, the
+Licensor for the purpose of discussing and improving the Work, but
+excluding communication that is conspicuously marked or otherwise
+designated in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity
+on behalf of whom a Contribution has been received by Licensor and
+subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+copyright license to reproduce, prepare Derivative Works of,
+publicly display, publicly perform, sublicense, and distribute the
+Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+(except as stated in this section) patent license to make, have made,
+use, offer to sell, sell, import, and otherwise transfer the Work,
+where such license applies only to those patent claims licensable
+by such Contributor that are necessarily infringed by their
+Contribution(s) alone or by combination of their Contribution(s)
+with the Work to which such Contribution(s) was submitted. If You
+institute patent litigation against any entity (including a
+cross-claim or counterclaim in a lawsuit) alleging that the Work
+or a Contribution incorporated within the Work constitutes direct
+or contributory patent infringement, then any patent licenses
+granted to You under this License for that Work shall terminate
+as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+Work or Derivative Works thereof in any medium, with or without
+modifications, and in Source or Object form, provided that You
+meet the following conditions:
+
+(a) You must give any other recipients of the Work or
+Derivative Works a copy of this License; and
+
+(b) You must cause any modified files to carry prominent notices
+stating that You changed the files; and
+
+(c) You must retain, in the Source form of any Derivative Works
+that You distribute, all copyright, patent, trademark, and
+attribution notices from the Source form of the Work,
+excluding those notices that do not pertain to any part of
+the Derivative Works; and
+
+(d) If the Work includes a "NOTICE" text file as part of its
+distribution, then any Derivative Works that You distribute must
+include a readable copy of the attribution notices contained
+within such NOTICE file, excluding those notices that do not
+pertain to any part of the Derivative Works, in at least one
+of the following places: within a NOTICE text file distributed
+as part of the Derivative Works; within the Source form or
+documentation, if provided along with the Derivative Works; or,
+within a display generated by the Derivative Works, if and
+wherever such third-party notices normally appear. The contents
+of the NOTICE file are for informational purposes only and
+do not modify the License. You may add Your own attribution
+notices within Derivative Works that You distribute, alongside
+or as an addendum to the NOTICE text from the Work, provided
+that such additional attribution notices cannot be construed
+as modifying the License.
+
+You may add Your own copyright statement to Your modifications and
+may provide additional or different license terms and conditions
+for use, reproduction, or distribution of Your modifications, or
+for any such Derivative Works as a whole, provided Your use,
+reproduction, and distribution of the Work otherwise complies with
+the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+any Contribution intentionally submitted for inclusion in the Work
+by You to the Licensor shall be under the terms and conditions of
+this License, without any additional terms or conditions.
+Notwithstanding the above, nothing herein shall supersede or modify
+the terms of any separate license agreement you may have executed
+with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+names, trademarks, service marks, or product names of the Licensor,
+except as required for reasonable and customary use in describing the
+origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+agreed to in writing, Licensor provides the Work (and each
+Contributor provides its Contributions) on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+implied, including, without limitation, any warranties or conditions
+of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+PARTICULAR PURPOSE. You are solely responsible for determining the
+appropriateness of using or redistributing the Work and assume any
+risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+whether in tort (including negligence), contract, or otherwise,
+unless required by applicable law (such as deliberate and grossly
+negligent acts) or agreed to in writing, shall any Contributor be
+liable to You for damages, including any direct, indirect, special,
+incidental, or consequential damages of any character arising as a
+result of this License or out of the use or inability to use the
+Work (including but not limited to damages for loss of goodwill,
+work stoppage, computer failure or malfunction, or any and all
+other commercial damages or losses), even if such Contributor
+has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+the Work or Derivative Works thereof, You may choose to offer,
+and charge a fee for, acceptance of support, warranty, indemnity,
+or other liability obligations and/or rights consistent with this
+License. However, in accepting such obligations, You may act only
+on Your own behalf and on Your sole responsibility, not on behalf
+of any other Contributor, and only if You agree to indemnify,
+defend, and hold each Contributor harmless for any liability
+incurred by, or claims asserted against, such Contributor by reason
+of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+To apply the Apache License to your work, attach the following
+boilerplate notice, with the fields enclosed by brackets "[]"
+replaced with your own identifying information. (Don't include
+the brackets!)  The text should be enclosed in the appropriate
+comment syntax for the file format. We also recommend that a
+file or class name and description of purpose be included on the
+same "printed page" as the copyright notice for easier
+identification within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

meshagent_commoncrawl-0.39.3/MANIFEST.in

@@ -0,0 +1,2 @@
+include README.md
+recursive-include meshagent/commoncrawl py.typed *.pyi

meshagent_commoncrawl-0.39.3/PKG-INFO

@@ -0,0 +1,51 @@
+Metadata-Version: 2.4
+Name: meshagent-commoncrawl
+Version: 0.39.3
+Summary: Common Crawl import support for Meshagent datasets
+License-Expression: Apache-2.0
+Project-URL: Documentation, https://docs.meshagent.com
+Project-URL: Website, https://www.meshagent.com
+Project-URL: Source, https://www.meshagent.com
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pytest~=8.4
+Requires-Dist: pytest-asyncio~=0.26
+Requires-Dist: meshagent-api==0.39.3
+Requires-Dist: pyarrow~=21.0.0
+Requires-Dist: warcio~=1.7
+Dynamic: license-file
+
+# Meshagent Common Crawl
+
+Import Common Crawl captures into a Meshagent room dataset.
+
+```python
+from meshagent.commoncrawl import import_domain_from_commoncrawl
+
+result = await import_domain_from_commoncrawl(
+    room,
+    index="CC-MAIN-2025-08",
+    domain="example.com",
+    table="pages",
+    url_filter=r"https?://(www\.)?example\.com/docs/.*",
+)
+```
+
+To test it through `meshagent room connect`:
+
+```bash
+meshagent room connect --room=my-room --identity=commoncrawl -- \
+  python meshagent-sdk/meshagent-commoncrawl/examples/crawl.py \
+  http://www.meshagent.com --table=sample --namespace=crawls --limit=10
+```
+
+The sample command writes progress to stderr while it imports. TTY output uses a
+single updating line; redirected output uses plain log lines. Pass `--silent` to
+suppress progress output.
+
+By default, records are merged on `url` with the columns `url`, `date`,
+`content_type`, and `text`. Pass an async `extract=` callback to derive custom
+columns from the WARC record and decoded content bytes. Return `None` from the
+callback to skip the record. Pass an async `progress=` callback to observe import
+progress from library code.

meshagent_commoncrawl-0.39.3/README.md

@@ -0,0 +1,33 @@
+# Meshagent Common Crawl
+
+Import Common Crawl captures into a Meshagent room dataset.
+
+```python
+from meshagent.commoncrawl import import_domain_from_commoncrawl
+
+result = await import_domain_from_commoncrawl(
+    room,
+    index="CC-MAIN-2025-08",
+    domain="example.com",
+    table="pages",
+    url_filter=r"https?://(www\.)?example\.com/docs/.*",
+)
+```
+
+To test it through `meshagent room connect`:
+
+```bash
+meshagent room connect --room=my-room --identity=commoncrawl -- \
+  python meshagent-sdk/meshagent-commoncrawl/examples/crawl.py \
+  http://www.meshagent.com --table=sample --namespace=crawls --limit=10
+```
+
+The sample command writes progress to stderr while it imports. TTY output uses a
+single updating line; redirected output uses plain log lines. Pass `--silent` to
+suppress progress output.
+
+By default, records are merged on `url` with the columns `url`, `date`,
+`content_type`, and `text`. Pass an async `extract=` callback to derive custom
+columns from the WARC record and decoded content bytes. Return `None` from the
+callback to skip the record. Pass an async `progress=` callback to observe import
+progress from library code.

meshagent_commoncrawl-0.39.3/meshagent/commoncrawl/__init__.py

@@ -0,0 +1,17 @@
+from .commoncrawl import (
+    CommonCrawlImportProgress,
+    CommonCrawlImportResult,
+    ExtractCallback,
+    ProgressCallback,
+    import_domain_from_commoncrawl,
+)
+from .version import __version__
+
+__all__ = [
+    "CommonCrawlImportResult",
+    "CommonCrawlImportProgress",
+    "ExtractCallback",
+    "ProgressCallback",
+    "__version__",
+    "import_domain_from_commoncrawl",
+]

meshagent_commoncrawl-0.39.3/meshagent/commoncrawl/commoncrawl.py

@@ -0,0 +1,595 @@
+from __future__ import annotations
+
+from collections.abc import AsyncIterator, Awaitable, Callable, Mapping, Sequence
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from html.parser import HTMLParser
+from io import BytesIO
+import json
+import logging
+from typing import TYPE_CHECKING, Any, TypeAlias
+from urllib.parse import parse_qsl, urlencode, urlparse
+
+import pyarrow as pa
+
+from meshagent.api import RoomClient
+from meshagent.api.http import new_client_session
+
+if TYPE_CHECKING:
+    from aiohttp import ClientSession
+    from warcio.recordloader import ArcWarcRecord
+
+logger = logging.getLogger(__name__)
+
+COMMONCRAWL_INDEX_BASE_URL = "https://index.commoncrawl.org"
+COMMONCRAWL_DATA_BASE_URL = "https://data.commoncrawl.org"
+
+ExtractedRecord: TypeAlias = Mapping[str, Any]
+ExtractCallback: TypeAlias = Callable[
+    ["ArcWarcRecord", bytes],
+    Awaitable[ExtractedRecord | None],
+]
+
+
+@dataclass(frozen=True)
+class CommonCrawlImportResult:
+    matched_records: int
+    imported_records: int
+    skipped_records: int
+    files_read: int
+
+
+@dataclass(frozen=True)
+class CommonCrawlImportProgress:
+    stage: str
+    matched_records: int
+    imported_records: int
+    skipped_records: int
+    files_read: int
+    pending_records: int
+    current_url: str | None = None
+    current_file: str | None = None
+
+
+ProgressCallback: TypeAlias = Callable[
+    [CommonCrawlImportProgress],
+    Awaitable[None],
+]
+
+
+@dataclass(frozen=True)
+class _CdxRecord:
+    url: str
+    timestamp: str
+    mime: str | None
+    filename: str
+    offset: int
+    length: int
+
+    @staticmethod
+    def from_json(value: Mapping[str, Any]) -> _CdxRecord:
+        url = value["url"]
+        timestamp = value["timestamp"]
+        filename = value["filename"]
+        offset = value["offset"]
+        length = value["length"]
+        if not isinstance(url, str):
+            raise ValueError("Common Crawl index record has non-string url")
+        if not isinstance(timestamp, str):
+            raise ValueError("Common Crawl index record has non-string timestamp")
+        if not isinstance(filename, str):
+            raise ValueError("Common Crawl index record has non-string filename")
+
+        mime_value = value.get("mime")
+        if mime_value is not None and not isinstance(mime_value, str):
+            mime_value = str(mime_value)
+
+        return _CdxRecord(
+            url=url,
+            timestamp=timestamp,
+            mime=mime_value,
+            filename=filename,
+            offset=int(offset),
+            length=int(length),
+        )
+
+
+class _TextExtractor(HTMLParser):
+    def __init__(self) -> None:
+        super().__init__(convert_charrefs=True)
+        self._parts: list[str] = []
+        self._hidden_depth = 0
+
+    def handle_starttag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:
+        del attrs
+        if tag.lower() in {"script", "style", "noscript"}:
+            self._hidden_depth += 1
+
+    def handle_endtag(self, tag: str) -> None:
+        if tag.lower() in {"script", "style", "noscript"} and self._hidden_depth > 0:
+            self._hidden_depth -= 1
+
+    def handle_data(self, data: str) -> None:
+        if self._hidden_depth == 0:
+            stripped = data.strip()
+            if stripped:
+                self._parts.append(stripped)
+
+    def text(self) -> str:
+        return " ".join(self._parts)
+
+
+async def import_domain_from_commoncrawl(
+    room: RoomClient,
+    *,
+    index: str,
+    domain: str,
+    table: str = "commoncrawl",
+    url_filter: str | Sequence[str] | None = None,
+    extract: ExtractCallback | None = None,
+    schema: pa.Schema | None = None,
+    primary_key: str = "url",
+    namespace: list[str] | None = None,
+    branch: str | None = None,
+    limit: int | None = None,
+    batch_size: int = 100,
+    session: "ClientSession | None" = None,
+    progress: ProgressCallback | None = None,
+) -> CommonCrawlImportResult:
+    """Import Common Crawl captures for a domain into a room dataset.
+
+    `url_filter` is passed to the Common Crawl CDX API as `filter=~url:<value>`.
+    Supply a sequence to pass multiple URL filters. The default extractor writes
+    `url`, `date`, `content_type`, and `text`, merging on `url`. Pass `schema`
+    when a custom extractor should create an empty table before the first row.
+    Pass `progress` to receive async progress updates during the import.
+    """
+
+    if batch_size <= 0:
+        raise ValueError("batch_size must be greater than zero")
+    if primary_key == "":
+        raise ValueError("primary_key must be non-empty")
+
+    close_session = session is None
+    http_session = session or new_client_session()
+    try:
+        return await _import_with_session(
+            room=room,
+            session=http_session,
+            index=index,
+            domain=domain,
+            table=table,
+            url_filter=url_filter,
+            extract=extract,
+            schema=schema,
+            primary_key=primary_key,
+            namespace=namespace,
+            branch=branch,
+            limit=limit,
+            batch_size=batch_size,
+            progress=progress,
+        )
+    finally:
+        if close_session:
+            await http_session.close()
+
+
+async def _import_with_session(
+    *,
+    room: RoomClient,
+    session: "ClientSession",
+    index: str,
+    domain: str,
+    table: str,
+    url_filter: str | Sequence[str] | None,
+    extract: ExtractCallback | None,
+    schema: pa.Schema | None,
+    primary_key: str,
+    namespace: list[str] | None,
+    branch: str | None,
+    limit: int | None,
+    batch_size: int,
+    progress: ProgressCallback | None,
+) -> CommonCrawlImportResult:
+    extractor = extract or _default_extract
+    schema = schema or (_default_schema() if extract is None else None)
+    if schema is not None:
+        await _ensure_table(
+            room=room,
+            table=table,
+            schema=schema,
+            namespace=namespace,
+            branch=branch,
+        )
+    matched_records = 0
+    imported_records = 0
+    skipped_records = 0
+    files_read = 0
+    batch: list[dict[str, Any]] = []
+    await _report_progress(
+        progress,
+        stage="started",
+        matched_records=matched_records,
+        imported_records=imported_records,
+        skipped_records=skipped_records,
+        files_read=files_read,
+        pending_records=len(batch),
+    )
+
+    async for index_record in _iter_index_records(
+        session=session,
+        index=index,
+        domain=domain,
+        url_filter=url_filter,
+        limit=limit,
+    ):
+        matched_records += 1
+        files_read += 1
+        await _report_progress(
+            progress,
+            stage="record_matched",
+            matched_records=matched_records,
+            imported_records=imported_records,
+            skipped_records=skipped_records,
+            files_read=files_read,
+            pending_records=len(batch),
+            current_url=index_record.url,
+            current_file=index_record.filename,
+        )
+        try:
+            async for warc_record, content in _iter_warc_records(
+                session=session,
+                index_record=index_record,
+            ):
+                extracted = await extractor(warc_record, content)
+                if extracted is None:
+                    skipped_records += 1
+                    await _report_progress(
+                        progress,
+                        stage="record_skipped",
+                        matched_records=matched_records,
+                        imported_records=imported_records,
+                        skipped_records=skipped_records,
+                        files_read=files_read,
+                        pending_records=len(batch),
+                        current_url=index_record.url,
+                        current_file=index_record.filename,
+                    )
+                    continue
+                row = dict(extracted)
+                if primary_key not in row:
+                    raise ValueError(
+                        f"extract callback must return primary key column {primary_key!r}"
+                    )
+                batch.append(row)
+                await _report_progress(
+                    progress,
+                    stage="record_extracted",
+                    matched_records=matched_records,
+                    imported_records=imported_records,
+                    skipped_records=skipped_records,
+                    files_read=files_read,
+                    pending_records=len(batch),
+                    current_url=index_record.url,
+                    current_file=index_record.filename,
+                )
+                if len(batch) >= batch_size:
+                    schema = await _merge_batch(
+                        room=room,
+                        table=table,
+                        rows=batch,
+                        schema=schema,
+                        primary_key=primary_key,
+                        namespace=namespace,
+                        branch=branch,
+                    )
+                    imported_records += len(batch)
+                    batch = []
+                    await _report_progress(
+                        progress,
+                        stage="batch_merged",
+                        matched_records=matched_records,
+                        imported_records=imported_records,
+                        skipped_records=skipped_records,
+                        files_read=files_read,
+                        pending_records=len(batch),
+                        current_url=index_record.url,
+                        current_file=index_record.filename,
+                    )
+        except Exception:
+            logger.exception(
+                "failed to import Common Crawl record %s from %s",
+                index_record.url,
+                index_record.filename,
+            )
+            raise
+
+    if batch:
+        await _merge_batch(
+            room=room,
+            table=table,
+            rows=batch,
+            schema=schema,
+            primary_key=primary_key,
+            namespace=namespace,
+            branch=branch,
+        )
+        imported_records += len(batch)
+        batch = []
+        await _report_progress(
+            progress,
+            stage="batch_merged",
+            matched_records=matched_records,
+            imported_records=imported_records,
+            skipped_records=skipped_records,
+            files_read=files_read,
+            pending_records=len(batch),
+        )
+
+    result = CommonCrawlImportResult(
+        matched_records=matched_records,
+        imported_records=imported_records,
+        skipped_records=skipped_records,
+        files_read=files_read,
+    )
+    await _report_progress(
+        progress,
+        stage="completed",
+        matched_records=result.matched_records,
+        imported_records=result.imported_records,
+        skipped_records=result.skipped_records,
+        files_read=result.files_read,
+        pending_records=0,
+    )
+    return result
+
+
+async def _report_progress(
+    progress: ProgressCallback | None,
+    *,
+    stage: str,
+    matched_records: int,
+    imported_records: int,
+    skipped_records: int,
+    files_read: int,
+    pending_records: int,
+    current_url: str | None = None,
+    current_file: str | None = None,
+) -> None:
+    if progress is None:
+        return
+    await progress(
+        CommonCrawlImportProgress(
+            stage=stage,
+            matched_records=matched_records,
+            imported_records=imported_records,
+            skipped_records=skipped_records,
+            files_read=files_read,
+            pending_records=pending_records,
+            current_url=current_url,
+            current_file=current_file,
+        )
+    )
+
+
+async def _merge_batch(
+    *,
+    room: RoomClient,
+    table: str,
+    rows: list[dict[str, Any]],
+    schema: pa.Schema | None,
+    primary_key: str,
+    namespace: list[str] | None,
+    branch: str | None,
+) -> pa.Schema:
+    next_schema = _merge_schema(
+        base=schema,
+        rows=rows,
+        primary_key=primary_key,
+    )
+    await _ensure_table(
+        room=room,
+        table=table,
+        schema=next_schema,
+        namespace=namespace,
+        branch=branch,
+    )
+    await room.datasets.merge(
+        table=table,
+        on=primary_key,
+        records=pa.Table.from_pylist(rows, schema=next_schema),
+        namespace=namespace,
+        branch=branch,
+    )
+    return next_schema
+
+
+async def _ensure_table(
+    *,
+    room: RoomClient,
+    table: str,
+    schema: pa.Schema,
+    namespace: list[str] | None,
+    branch: str | None,
+) -> None:
+    await room.datasets.create_table_with_schema(
+        name=table,
+        schema=schema,
+        mode="create_if_not_exists",
+        namespace=namespace,
+        branch=branch,
+    )
+    existing_schema = await room.datasets.inspect(
+        table=table,
+        namespace=namespace,
+        branch=branch,
+    )
+    existing_names = set(existing_schema.names)
+    missing_fields = {
+        field.name: field for field in schema if field.name not in existing_names
+    }
+    if missing_fields:
+        await room.datasets.add_columns(
+            table=table,
+            new_columns=missing_fields,
+            namespace=namespace,
+            branch=branch,
+        )
+
+
+async def _iter_index_records(
+    *,
+    session: "ClientSession",
+    index: str,
+    domain: str,
+    url_filter: str | Sequence[str] | None,
+    limit: int | None,
+) -> AsyncIterator[_CdxRecord]:
+    params: list[tuple[str, str]] = [
+        ("url", _domain_index_query(domain)),
+        ("matchType", "domain"),
+        ("output", "json"),
+        ("fl", "url,timestamp,mime,filename,offset,length"),
+        ("filter", "status:200"),
+    ]
+    for filter_value in _url_filters(url_filter):
+        params.append(("filter", f"~url:{filter_value}"))
+    if limit is not None:
+        params.append(("limit", str(limit)))
+
+    url = f"{_index_base_url(index)}?{urlencode(params)}"
+    async with session.get(url) as response:
+        if response.status == 404:
+            return
+        response.raise_for_status()
+        async for raw_line in response.content:
+            line = raw_line.decode("utf-8").strip()
+            if line == "":
+                continue
+            yield _CdxRecord.from_json(json.loads(line))
+
+
+async def _iter_warc_records(
+    *,
+    session: "ClientSession",
+    index_record: _CdxRecord,
+) -> AsyncIterator[tuple["ArcWarcRecord", bytes]]:
+    from warcio.archiveiterator import ArchiveIterator
+
+    end = index_record.offset + index_record.length - 1
+    headers = {"Range": f"bytes={index_record.offset}-{end}"}
+    url = f"{COMMONCRAWL_DATA_BASE_URL}/{index_record.filename}"
+
+    async with session.get(url, headers=headers) as response:
+        response.raise_for_status()
+        data = await response.read()
+
+    for warc_record in ArchiveIterator(BytesIO(data)):
+        if warc_record.rec_type != "response":
+            continue
+        yield warc_record, warc_record.content_stream().read()
+
+
+async def _default_extract(record: "ArcWarcRecord", content: bytes) -> dict[str, str]:
+    content_type = _content_type(record)
+    text = _content_text(content=content, content_type=content_type)
+    return {
+        "url": record.rec_headers.get_header("WARC-Target-URI") or "",
+        "date": _warc_date(record.rec_headers.get_header("WARC-Date")),
+        "content_type": content_type,
+        "text": text,
+    }
+
+
+def _content_type(record: "ArcWarcRecord") -> str:
+    content_type = ""
+    if record.http_headers is not None:
+        content_type = record.http_headers.get_header("Content-Type") or ""
+    if content_type == "":
+        content_type = record.rec_headers.get_header("Content-Type") or ""
+    return content_type
+
+
+def _warc_date(value: str | None) -> str:
+    if value is None or value == "":
+        return ""
+    try:
+        parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
+    except ValueError:
+        return value
+    return parsed.astimezone(timezone.utc).isoformat().replace("+00:00", "Z")
+
+
+def _content_text(*, content: bytes, content_type: str) -> str:
+    charset = _charset(content_type)
+    decoded = content.decode(charset, errors="replace")
+    normalized_content_type = content_type.lower()
+    if "html" not in normalized_content_type and "xml" not in normalized_content_type:
+        return decoded
+
+    parser = _TextExtractor()
+    parser.feed(decoded)
+    parser.close()
+    return parser.text()
+
+
+def _charset(content_type: str) -> str:
+    for key, value in parse_qsl(content_type.replace(";", "&"), keep_blank_values=True):
+        if key.strip().lower() == "charset" and value.strip() != "":
+            return value.strip()
+    return "utf-8"
+
+
+def _default_schema() -> pa.Schema:
+    return pa.schema(
+        [
+            pa.field("url", pa.string(), nullable=False),
+            pa.field("date", pa.string()),
+            pa.field("content_type", pa.string()),
+            pa.field("text", pa.string()),
+        ]
+    )
+
+
+def _merge_schema(
+    *,
+    base: pa.Schema | None,
+    rows: list[dict[str, Any]],
+    primary_key: str,
+) -> pa.Schema:
+    inferred = pa.Table.from_pylist(rows).schema
+    fields_by_name = {field.name: field for field in base} if base is not None else {}
+    for field in inferred:
+        if pa.types.is_null(field.type):
+            field = pa.field(field.name, pa.string(), nullable=field.nullable)
+        if field.name == primary_key:
+            field = pa.field(field.name, field.type, nullable=False)
+        fields_by_name.setdefault(field.name, field)
+
+    if primary_key not in fields_by_name:
+        raise ValueError(f"rows must include primary key column {primary_key!r}")
+    return pa.schema(list(fields_by_name.values()))
+
+
+def _domain_index_query(domain: str) -> str:
+    parsed = urlparse(domain)
+    host = parsed.netloc or parsed.path.split("/", maxsplit=1)[0]
+    normalized = host.strip().strip(".").lower()
+    if normalized == "":
+        raise ValueError("domain must be non-empty")
+    return normalized
+
+
+def _url_filters(url_filter: str | Sequence[str] | None) -> list[str]:
+    if url_filter is None:
+        return []
+    if isinstance(url_filter, str):
+        return [url_filter]
+    return list(url_filter)
+
+
+def _index_base_url(index: str) -> str:
+    if index.startswith("http://") or index.startswith("https://"):
+        return index
+    normalized = index if index.endswith("-index") else f"{index}-index"
+    return f"{COMMONCRAWL_INDEX_BASE_URL}/{normalized}"

meshagent_commoncrawl-0.39.3/meshagent/commoncrawl/py.typed

@@ -0,0 +1 @@
+

meshagent_commoncrawl-0.39.3/meshagent/commoncrawl/version.py

@@ -0,0 +1 @@
+__version__ = "0.39.3"

meshagent_commoncrawl-0.39.3/meshagent_commoncrawl.egg-info/PKG-INFO

@@ -0,0 +1,51 @@
+Metadata-Version: 2.4
+Name: meshagent-commoncrawl
+Version: 0.39.3
+Summary: Common Crawl import support for Meshagent datasets
+License-Expression: Apache-2.0
+Project-URL: Documentation, https://docs.meshagent.com
+Project-URL: Website, https://www.meshagent.com
+Project-URL: Source, https://www.meshagent.com
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pytest~=8.4
+Requires-Dist: pytest-asyncio~=0.26
+Requires-Dist: meshagent-api==0.39.3
+Requires-Dist: pyarrow~=21.0.0
+Requires-Dist: warcio~=1.7
+Dynamic: license-file
+
+# Meshagent Common Crawl
+
+Import Common Crawl captures into a Meshagent room dataset.
+
+```python
+from meshagent.commoncrawl import import_domain_from_commoncrawl
+
+result = await import_domain_from_commoncrawl(
+    room,
+    index="CC-MAIN-2025-08",
+    domain="example.com",
+    table="pages",
+    url_filter=r"https?://(www\.)?example\.com/docs/.*",
+)
+```
+
+To test it through `meshagent room connect`:
+
+```bash
+meshagent room connect --room=my-room --identity=commoncrawl -- \
+  python meshagent-sdk/meshagent-commoncrawl/examples/crawl.py \
+  http://www.meshagent.com --table=sample --namespace=crawls --limit=10
+```
+
+The sample command writes progress to stderr while it imports. TTY output uses a
+single updating line; redirected output uses plain log lines. Pass `--silent` to
+suppress progress output.
+
+By default, records are merged on `url` with the columns `url`, `date`,
+`content_type`, and `text`. Pass an async `extract=` callback to derive custom
+columns from the WARC record and decoded content bytes. Return `None` from the
+callback to skip the record. Pass an async `progress=` callback to observe import
+progress from library code.

meshagent_commoncrawl-0.39.3/meshagent_commoncrawl.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+meshagent/commoncrawl/__init__.py
+meshagent/commoncrawl/commoncrawl.py
+meshagent/commoncrawl/py.typed
+meshagent/commoncrawl/version.py
+meshagent_commoncrawl.egg-info/PKG-INFO
+meshagent_commoncrawl.egg-info/SOURCES.txt
+meshagent_commoncrawl.egg-info/dependency_links.txt
+meshagent_commoncrawl.egg-info/requires.txt
+meshagent_commoncrawl.egg-info/top_level.txt
+tests/test_commoncrawl.py

meshagent_commoncrawl-0.39.3/meshagent_commoncrawl.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

meshagent_commoncrawl-0.39.3/meshagent_commoncrawl.egg-info/requires.txt

@@ -0,0 +1,5 @@
+pytest~=8.4
+pytest-asyncio~=0.26
+meshagent-api==0.39.3
+pyarrow~=21.0.0
+warcio~=1.7

meshagent_commoncrawl-0.39.3/meshagent_commoncrawl.egg-info/top_level.txt

@@ -0,0 +1 @@
+meshagent

meshagent_commoncrawl-0.39.3/pyproject.toml

@@ -0,0 +1,32 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "meshagent-commoncrawl"
+description = "Common Crawl import support for Meshagent datasets"
+dynamic = ["version", "readme"]
+requires-python = ">=3.13"
+license = "Apache-2.0"
+dependencies = [
+  "pytest~=8.4",
+  "pytest-asyncio~=0.26",
+  "meshagent-api==0.39.3",
+  "pyarrow~=21.0.0",
+  "warcio~=1.7",
+]
+
+[project.urls]
+Documentation = "https://docs.meshagent.com"
+Website = "https://www.meshagent.com"
+Source = "https://www.meshagent.com"
+
+[tool.setuptools.packages.find]
+include = ["meshagent.*"]
+
+[tool.setuptools.package-data]
+"meshagent.commoncrawl" = ["py.typed", "*.pyi", "**/*.pyi"]
+
+[tool.setuptools.dynamic]
+version = {attr = "meshagent.commoncrawl.version.__version__"}
+readme = { file = "README.md", content-type = "text/markdown" }

meshagent_commoncrawl-0.39.3/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

meshagent_commoncrawl-0.39.3/tests/test_commoncrawl.py

@@ -0,0 +1,301 @@
+from __future__ import annotations
+
+from collections.abc import AsyncIterator
+from dataclasses import dataclass
+from typing import Any
+
+import pyarrow as pa
+import pytest
+
+from meshagent.commoncrawl import commoncrawl
+from meshagent.commoncrawl.commoncrawl import CommonCrawlImportProgress, _CdxRecord
+
+
+class _Headers:
+    def __init__(self, values: dict[str, str]) -> None:
+        self._values = values
+
+    def get_header(self, name: str) -> str | None:
+        return self._values.get(name)
+
+
+class _WarcRecord:
+    rec_type = "response"
+
+    def __init__(self, *, url: str, date: str, content_type: str) -> None:
+        self.rec_headers = _Headers(
+            {
+                "WARC-Target-URI": url,
+                "WARC-Date": date,
+                "Content-Type": "application/http; msgtype=response",
+            }
+        )
+        self.http_headers = _Headers({"Content-Type": content_type})
+
+
+class _FakeDatasets:
+    def __init__(self) -> None:
+        self.schema: pa.Schema | None = None
+        self.create_calls: list[dict[str, Any]] = []
+        self.add_columns_calls: list[dict[str, Any]] = []
+        self.merge_calls: list[dict[str, Any]] = []
+
+    async def create_table_with_schema(
+        self,
+        *,
+        name: str,
+        schema: pa.Schema,
+        mode: str,
+        namespace: list[str] | None = None,
+        branch: str | None = None,
+    ) -> None:
+        self.create_calls.append(
+            {
+                "name": name,
+                "schema": schema,
+                "mode": mode,
+                "namespace": namespace,
+                "branch": branch,
+            }
+        )
+        if self.schema is None:
+            self.schema = schema
+
+    async def inspect(
+        self,
+        *,
+        table: str,
+        namespace: list[str] | None = None,
+        branch: str | None = None,
+    ) -> pa.Schema:
+        del table, namespace, branch
+        return self.schema or pa.schema([])
+
+    async def add_columns(
+        self,
+        *,
+        table: str,
+        new_columns: dict[str, pa.Field],
+        namespace: list[str] | None = None,
+        branch: str | None = None,
+    ) -> None:
+        self.add_columns_calls.append(
+            {
+                "table": table,
+                "new_columns": new_columns,
+                "namespace": namespace,
+                "branch": branch,
+            }
+        )
+        assert self.schema is not None
+        self.schema = self.schema.append(next(iter(new_columns.values())))
+
+    async def merge(
+        self,
+        *,
+        table: str,
+        on: str,
+        records: pa.Table,
+        namespace: list[str] | None = None,
+        branch: str | None = None,
+    ) -> None:
+        self.merge_calls.append(
+            {
+                "table": table,
+                "on": on,
+                "records": records,
+                "namespace": namespace,
+                "branch": branch,
+            }
+        )
+
+
+@dataclass
+class _FakeRoom:
+    datasets: _FakeDatasets
+
+
+class _FakeSession:
+    async def close(self) -> None:
+        return None
+
+
+async def _fake_index_records(**kwargs: Any) -> AsyncIterator[_CdxRecord]:
+    del kwargs
+    yield _CdxRecord(
+        url="https://example.com/a",
+        timestamp="20240101000000",
+        mime="text/html",
+        filename="crawl/a.warc.gz",
+        offset=0,
+        length=10,
+    )
+    yield _CdxRecord(
+        url="https://example.com/b",
+        timestamp="20240101000001",
+        mime="text/html",
+        filename="crawl/b.warc.gz",
+        offset=10,
+        length=10,
+    )
+
+
+async def _fake_warc_records(
+    *,
+    index_record: _CdxRecord,
+    **kwargs: Any,
+) -> AsyncIterator[tuple[_WarcRecord, bytes]]:
+    del kwargs
+    yield (
+        _WarcRecord(
+            url=index_record.url,
+            date="2024-01-01T00:00:00Z",
+            content_type="text/html; charset=utf-8",
+        ),
+        b"<html><head><style>.x{}</style></head><body>Hello <b>page</b></body></html>",
+    )
+
+
+@pytest.mark.asyncio
+async def test_import_domain_uses_default_columns_and_merge(monkeypatch) -> None:
+    monkeypatch.setattr(commoncrawl, "_iter_index_records", _fake_index_records)
+    monkeypatch.setattr(commoncrawl, "_iter_warc_records", _fake_warc_records)
+    room = _FakeRoom(datasets=_FakeDatasets())
+
+    result = await commoncrawl.import_domain_from_commoncrawl(
+        room,  # type: ignore[arg-type]
+        index="CC-MAIN-2025-08",
+        domain="example.com",
+        table="pages",
+        batch_size=1,
+        session=_FakeSession(),  # type: ignore[arg-type]
+    )
+
+    assert result.matched_records == 2
+    assert result.imported_records == 2
+    assert result.skipped_records == 0
+    assert room.datasets.create_calls[0]["mode"] == "create_if_not_exists"
+    assert room.datasets.merge_calls[0]["on"] == "url"
+    assert room.datasets.merge_calls[0]["records"].to_pylist() == [
+        {
+            "url": "https://example.com/a",
+            "date": "2024-01-01T00:00:00Z",
+            "content_type": "text/html; charset=utf-8",
+            "text": "Hello page",
+        }
+    ]
+
+
+@pytest.mark.asyncio
+async def test_extract_callback_can_filter_records(monkeypatch) -> None:
+    monkeypatch.setattr(commoncrawl, "_iter_index_records", _fake_index_records)
+    monkeypatch.setattr(commoncrawl, "_iter_warc_records", _fake_warc_records)
+    room = _FakeRoom(datasets=_FakeDatasets())
+
+    async def extract(record: _WarcRecord, content: bytes) -> dict[str, str] | None:
+        del content
+        url = record.rec_headers.get_header("WARC-Target-URI") or ""
+        if url.endswith("/b"):
+            return None
+        return {"url": url, "title": "A"}
+
+    result = await commoncrawl.import_domain_from_commoncrawl(
+        room,  # type: ignore[arg-type]
+        index="CC-MAIN-2025-08",
+        domain="example.com",
+        extract=extract,  # type: ignore[arg-type]
+        session=_FakeSession(),  # type: ignore[arg-type]
+    )
+
+    assert result.matched_records == 2
+    assert result.imported_records == 1
+    assert result.skipped_records == 1
+    assert room.datasets.merge_calls[0]["records"].to_pylist() == [
+        {"url": "https://example.com/a", "title": "A"}
+    ]
+
+
+@pytest.mark.asyncio
+async def test_import_domain_reports_progress(monkeypatch) -> None:
+    monkeypatch.setattr(commoncrawl, "_iter_index_records", _fake_index_records)
+    monkeypatch.setattr(commoncrawl, "_iter_warc_records", _fake_warc_records)
+    room = _FakeRoom(datasets=_FakeDatasets())
+    updates: list[CommonCrawlImportProgress] = []
+
+    async def progress(update: CommonCrawlImportProgress) -> None:
+        updates.append(update)
+
+    result = await commoncrawl.import_domain_from_commoncrawl(
+        room,  # type: ignore[arg-type]
+        index="CC-MAIN-2025-08",
+        domain="example.com",
+        batch_size=2,
+        session=_FakeSession(),  # type: ignore[arg-type]
+        progress=progress,
+    )
+
+    assert result.imported_records == 2
+    assert [update.stage for update in updates] == [
+        "started",
+        "record_matched",
+        "record_extracted",
+        "record_matched",
+        "record_extracted",
+        "batch_merged",
+        "completed",
+    ]
+    assert updates[-1].matched_records == 2
+    assert updates[-1].imported_records == 2
+    assert updates[-1].pending_records == 0
+
+
+def test_commoncrawl_index_url_helpers() -> None:
+    assert commoncrawl._domain_index_query("https://Example.COM/docs") == "example.com"
+    assert commoncrawl._url_filters(["a", "b"]) == ["a", "b"]
+    assert commoncrawl._index_base_url("CC-MAIN-2025-08").endswith(
+        "/CC-MAIN-2025-08-index"
+    )
+
+
+@pytest.mark.asyncio
+async def test_index_404_is_treated_as_no_matches() -> None:
+    class _Content:
+        def __aiter__(self) -> AsyncIterator[bytes]:
+            return self._iter()
+
+        async def _iter(self) -> AsyncIterator[bytes]:
+            if False:
+                yield b""
+
+    class _Response:
+        status = 404
+        content = _Content()
+
+        async def __aenter__(self) -> _Response:
+            return self
+
+        async def __aexit__(self, *args: object) -> None:
+            return None
+
+        def raise_for_status(self) -> None:
+            raise AssertionError("404 should not raise")
+
+    class _Session:
+        def get(self, url: str) -> _Response:
+            assert "matchType=domain" in url
+            assert "url=www.hersheyland.com" in url
+            assert "filter=~url%3A%5Ehttps%3F%3A%2F%2Fwww" in url
+            return _Response()
+
+    rows = [
+        row
+        async for row in commoncrawl._iter_index_records(
+            session=_Session(),  # type: ignore[arg-type]
+            index="CC-MAIN-2025-08",
+            domain="www.hersheyland.com",
+            url_filter=r"^https?://www\.hersheyland\.com(/.*)?$",
+            limit=None,
+        )
+    ]
+
+    assert rows == []