github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-21 14:18:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

upstage[minor]: Update few codes and add upstage loader in pdf section (#21085)

Browse Source 
**Description:** Update UpstageLayoutAnalysisParser and Loader and add
upstage loader example in pdf section
**Dependencies:** langchain_community
**Twitter handle:** [@upstageai](https://twitter.com/upstageai)

- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.


- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
This commit is contained in:
junkeon 2024-05-01 09:15:49 +09:00 committed by GitHub
parent bef50ded63
commit 8d2909ee25
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 173 additions and 134 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
docs/docs/modules/data_connection/document_loaders/pdf.mdx
View File

@ -475,4 +475,31 @@ loader = AzureAIDocumentIntelligenceLoader(
) )
documents = loader.load() documents = loader.load()
``` ```
## Using UpstageLayoutAnalysisLoader
The UpstageLayoutAnalysisLoader invokes the [Upstage Layout Analysis API](https://developers.upstage.ai/docs/apis/layout-analyzer) to detect document elements, including tables and figures, from various document formats. This loader employs pure OCR to extract textual information and detect elements within documents such as `JPEG`, `PNG`, `BMP`, `PDF`, `TIFF`, and `HEIC` files. In the case of digital born PDF documents, users have the option to forego OCR and utilize text information within the file by setting use_ocr=False, which is the default value. Both single and multi-page documents are supported, with a limit of 100 pages and a file size of 50 MB when use_ocr=True, while there are no restrictions when use_ocr=False (applicable to PDF files only).
### Prerequisite
To access the Upstage Layout Analysis API, you require an API access token. Kindly refer to the [quick start guide](https://developers.upstage.ai/docs/getting-started/quick-start) provided to obtain the access token and begin utilizing the Upstage Layout Analysis API.
```bash
pip install langchain_upstage
```
### Example
```python
import os
os.environ["UPSTAGE_DOCUMENT_AI_API_KEY"] = "YOUR_API_KEY"
from langchain_upstage import UpstageLayoutAnalysisLoader
file_path = "/PATH/TO/FILE.pdf"
loader = UpstageLayoutAnalysisLoader(file_path)
data = loader.load()
```

13
libs/partners/upstage/langchain_upstage/layout_analysis.py
View File

@ -90,10 +90,11 @@ class UpstageLayoutAnalysisLoader(BaseLoader):
def __init__( def __init__(
self, self,
file_path: Union[str, Path, List[str], List[Path]], file_path: Union[str, Path, List[str], List[Path]],
output_type: Union[OutputType, dict] = "text", output_type: Union[OutputType, dict] = "html",
split: SplitType = "none", split: SplitType = "none",
api_key: Optional[str] = None, api_key: Optional[str] = None,
use_ocr: bool = False, use_ocr: bool = False,
exclude: list = ["header", "footer"],
): ):
""" """
Initializes an instance of the Upstage document loader. Initializes an instance of the Upstage document loader.
@ -103,7 +104,7 @@ class UpstageLayoutAnalysisLoader(BaseLoader):
to be loaded. to be loaded.
output_type (Union[OutputType, dict], optional): The type of output to be output_type (Union[OutputType, dict], optional): The type of output to be
generated by the parser. generated by the parser.
Defaults to "text". Defaults to "html".
split (SplitType, optional): The type of splitting to be applied. split (SplitType, optional): The type of splitting to be applied.
Defaults to "none" (no splitting). Defaults to "none" (no splitting).
api_key (str, optional): The API key for accessing the Upstage API. api_key (str, optional): The API key for accessing the Upstage API.
@ -112,6 +113,9 @@ class UpstageLayoutAnalysisLoader(BaseLoader):
`UPSTAGE_DOCUMENT_AI_API_KEY`. `UPSTAGE_DOCUMENT_AI_API_KEY`.
use_ocr (bool, optional): Extract text from images in the document. use_ocr (bool, optional): Extract text from images in the document.
Defaults to False. (Use text info in PDF file) Defaults to False. (Use text info in PDF file)
exclude (list, optional): Exclude specific elements from
the output.
Defaults to ["header", "footer"].
""" """
self.file_path = file_path self.file_path = file_path
self.output_type = output_type self.output_type = output_type
@ -120,6 +124,7 @@ class UpstageLayoutAnalysisLoader(BaseLoader):
"UPSTAGE_DOCUMENT_AI_API_KEY", api_key, "UPSTAGE_DOCUMENT_AI_API_KEY" "UPSTAGE_DOCUMENT_AI_API_KEY", api_key, "UPSTAGE_DOCUMENT_AI_API_KEY"
) )
self.use_ocr = use_ocr self.use_ocr = use_ocr
self.exclude = exclude
validate_file_path(self.file_path) validate_file_path(self.file_path)
validate_api_key(self.api_key) validate_api_key(self.api_key)
@ -143,6 +148,7 @@ class UpstageLayoutAnalysisLoader(BaseLoader):
split=self.split, split=self.split,
output_type=self.output_type, output_type=self.output_type,
use_ocr=self.use_ocr, use_ocr=self.use_ocr,
exclude=self.exclude,
) )
result.extend(list(parser.lazy_parse(blob, is_batch=True))) result.extend(list(parser.lazy_parse(blob, is_batch=True)))
@ -156,6 +162,7 @@ class UpstageLayoutAnalysisLoader(BaseLoader):
split=self.split, split=self.split,
output_type=self.output_type, output_type=self.output_type,
use_ocr=self.use_ocr, use_ocr=self.use_ocr,
exclude=self.exclude,
) )
return list(parser.lazy_parse(blob, is_batch=True)) return list(parser.lazy_parse(blob, is_batch=True))
@ -176,6 +183,7 @@ class UpstageLayoutAnalysisLoader(BaseLoader):
split=self.split, split=self.split,
output_type=self.output_type, output_type=self.output_type,
use_ocr=self.use_ocr, use_ocr=self.use_ocr,
exclude=self.exclude,
) )
yield from parser.lazy_parse(blob, is_batch=True) yield from parser.lazy_parse(blob, is_batch=True)
else: else:
@ -186,5 +194,6 @@ class UpstageLayoutAnalysisLoader(BaseLoader):
split=self.split, split=self.split,
output_type=self.output_type, output_type=self.output_type,
use_ocr=self.use_ocr, use_ocr=self.use_ocr,
exclude=self.exclude,
) )
yield from parser.lazy_parse(blob) yield from parser.lazy_parse(blob)

54
libs/partners/upstage/langchain_upstage/layout_analysis_parsers.py
View File

@ -117,9 +117,10 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
def __init__( def __init__(
self, self,
api_key: Optional[str] = None, api_key: Optional[str] = None,
output_type: Union[OutputType, dict] = "text", output_type: Union[OutputType, dict] = "html",
split: SplitType = "none", split: SplitType = "none",
use_ocr: bool = False, use_ocr: bool = False,
exclude: list = [],
): ):
""" """
Initializes an instance of the Upstage class. Initializes an instance of the Upstage class.
@ -131,11 +132,13 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
`UPSTAGE_DOCUMENT_AI_API_KEY`. `UPSTAGE_DOCUMENT_AI_API_KEY`.
output_type (Union[OutputType, dict], optional): The type of output to be output_type (Union[OutputType, dict], optional): The type of output to be
generated by the parser. generated by the parser.
Defaults to "text". Defaults to "html".
split (SplitType, optional): The type of splitting to be applied. split (SplitType, optional): The type of splitting to be applied.
Defaults to "none" (no splitting). Defaults to "none" (no splitting).
use_ocr (bool, optional): Extract text from images in the document. use_ocr (bool, optional): Extract text from images in the document.
Defaults to False. (Use text info in PDF file) Defaults to False. (Use text info in PDF file)
exclude (list, optional): Exclude specific elements from the output.
Defaults to [] (all included).
""" """
self.api_key = get_from_param_or_env( self.api_key = get_from_param_or_env(
"UPSTAGE_DOCUMENT_AI_API_KEY", api_key, "UPSTAGE_DOCUMENT_AI_API_KEY" "UPSTAGE_DOCUMENT_AI_API_KEY", api_key, "UPSTAGE_DOCUMENT_AI_API_KEY"
@ -144,10 +147,11 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
self.output_type = output_type self.output_type = output_type
self.split = split self.split = split
self.use_ocr = use_ocr self.use_ocr = use_ocr
self.exclude = exclude
validate_api_key(self.api_key) validate_api_key(self.api_key)
def _get_response(self, files: Dict) -> Dict: def _get_response(self, files: Dict) -> List:
""" """
Sends a POST request to the API endpoint with the provided files and Sends a POST request to the API endpoint with the provided files and
returns the response. returns the response.
@ -165,11 +169,11 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
headers = {"Authorization": f"Bearer {self.api_key}"} headers = {"Authorization": f"Bearer {self.api_key}"}
options = {"ocr": self.use_ocr} options = {"ocr": self.use_ocr}
response = requests.post( response = requests.post(
LAYOUT_ANALYSIS_URL, headers=headers, files=files, json=options LAYOUT_ANALYSIS_URL, headers=headers, files=files, data=options
) )
response.raise_for_status() response.raise_for_status()
result = response.json() result = response.json().get("elements", [])
except requests.RequestException as req_err: except requests.RequestException as req_err:
# Handle any request-related exceptions # Handle any request-related exceptions
@ -179,14 +183,18 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
print(f"JSON Decode Error: {json_err}") print(f"JSON Decode Error: {json_err}")
raise ValueError(f"Failed to decode JSON response: {json_err}") raise ValueError(f"Failed to decode JSON response: {json_err}")
return result elements = [
element for element in result if element["category"] not in self.exclude
]
return elements
def _split_and_request( def _split_and_request(
self, self,
full_docs: fitzDocument, full_docs: fitzDocument,
start_page: int, start_page: int,
num_pages: int = DEFAULT_NUMBER_OF_PAGE, num_pages: int = DEFAULT_NUMBER_OF_PAGE,
) -> Dict: ) -> List:
""" """
Splits the full pdf document into partial pages and sends a request to the Splits the full pdf document into partial pages and sends a request to the
server. server.
@ -235,12 +243,12 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
}, },
) )
def _page_document(self, elements: Dict) -> List[Document]: def _page_document(self, elements: List) -> List[Document]:
""" """
Combines elements with the same page number into a single Document object. Combines elements with the same page number into a single Document object.
Args: Args:
elements (List[Dict]): A list of elements containing page numbers. elements (List): A list of elements containing page numbers.
Returns: Returns:
List[Document]: A list of Document objects, each representing a page List[Document]: A list of Document objects, each representing a page
@ -306,17 +314,22 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
if start_page >= number_of_pages: if start_page >= number_of_pages:
break break
response = self._split_and_request(full_docs, start_page, num_pages) elements = self._split_and_request(full_docs, start_page, num_pages)
result += parse_output(response, self.output_type) for element in elements:
result += parse_output(element, self.output_type)
start_page += num_pages start_page += num_pages
else: else:
if not blob.path: if not blob.path:
raise ValueError("Blob path is required for non-PDF files.") raise ValueError("Blob path is required for non-PDF files.")
result = ""
with open(blob.path, "rb") as f: with open(blob.path, "rb") as f:
response = self._get_response({"document": f}) elements = self._get_response({"document": f})
result = parse_output(response, self.output_type)
for element in elements:
result += parse_output(element, self.output_type)
yield Document( yield Document(
page_content=result, page_content=result,
@ -334,8 +347,8 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
if start_page >= number_of_pages: if start_page >= number_of_pages:
break break
response = self._split_and_request(full_docs, start_page, num_pages) elements = self._split_and_request(full_docs, start_page, num_pages)
for element in response["elements"]: for element in elements:
yield self._element_document(element) yield self._element_document(element)
start_page += num_pages start_page += num_pages
@ -344,9 +357,9 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
if not blob.path: if not blob.path:
raise ValueError("Blob path is required for non-PDF files.") raise ValueError("Blob path is required for non-PDF files.")
with open(blob.path, "rb") as f: with open(blob.path, "rb") as f:
response = self._get_response({"document": f}) elements = self._get_response({"document": f})
for element in response["elements"]: for element in elements:
yield self._element_document(element) yield self._element_document(element)
elif self.split == "page": elif self.split == "page":
@ -356,8 +369,7 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
if start_page >= number_of_pages: if start_page >= number_of_pages:
break break
response = self._split_and_request(full_docs, start_page, num_pages) elements = self._split_and_request(full_docs, start_page, num_pages)
elements = response["elements"]
yield from self._page_document(elements) yield from self._page_document(elements)
start_page += num_pages start_page += num_pages
@ -365,9 +377,7 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
if not blob.path: if not blob.path:
raise ValueError("Blob path is required for non-PDF files.") raise ValueError("Blob path is required for non-PDF files.")
with open(blob.path, "rb") as f: with open(blob.path, "rb") as f:
response = self._get_response({"document": f}) elements = self._get_response({"document": f})
elements = response["elements"]
yield from self._page_document(elements) yield from self._page_document(elements)

200
libs/partners/upstage/poetry.lock generated
View File

@ -1,4 +1,4 @@
# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand. # This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
[[package]] [[package]]
name = "anyio" name = "anyio"
@ -364,7 +364,7 @@ url = "../../core"
[[package]] [[package]]
name = "langchain-openai" name = "langchain-openai"
version = "0.1.3" version = "0.1.4"
description = "An integration package connecting OpenAI and LangChain" description = "An integration package connecting OpenAI and LangChain"
optional = false optional = false
python-versions = ">=3.8.1,<4.0" python-versions = ">=3.8.1,<4.0"
@ -372,7 +372,7 @@ files = []
develop = true develop = true
[package.dependencies] [package.dependencies]
langchain-core = "^0.1.42" langchain-core = "^0.1.46"
openai = "^1.10.0" openai = "^1.10.0"
tiktoken = ">=0.5.2,<1" tiktoken = ">=0.5.2,<1"
@ -399,13 +399,13 @@ url = "../../standard-tests"
[[package]] [[package]]
name = "langsmith" name = "langsmith"
version = "0.1.50" version = "0.1.52"
description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform." description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
optional = false optional = false
python-versions = "<4.0,>=3.8.1" python-versions = "<4.0,>=3.8.1"
files = [ files = [
{file = "langsmith-0.1.50-py3-none-any.whl", hash = "sha256:a81e9809fcaa277bfb314d729e58116554f186d1478fcfdf553b1c2ccce54b85"}, {file = "langsmith-0.1.52-py3-none-any.whl", hash = "sha256:4518e269b9a0e10197550f050b6518d1276fe68732f7b8579b3e1302b8471d29"},
{file = "langsmith-0.1.50.tar.gz", hash = "sha256:9fd22df8c689c044058536ea5af66f5302067e7551b60d7a335fede8d479572b"}, {file = "langsmith-0.1.52.tar.gz", hash = "sha256:f767fddb13c794bea7cc827a77f050a8a1c075ab1d997eb37849b975b0eef1b0"},
] ]
[package.dependencies] [package.dependencies]
@ -548,13 +548,13 @@ files = [
[[package]] [[package]]
name = "openai" name = "openai"
version = "1.23.6" version = "1.24.0"
description = "The official Python library for the openai API" description = "The official Python library for the openai API"
optional = false optional = false
python-versions = ">=3.7.1" python-versions = ">=3.7.1"
files = [ files = [
{file = "openai-1.23.6-py3-none-any.whl", hash = "sha256:f406c76ba279d16b9aca5a89cee0d968488e39f671f4dc6f0d690ac3c6f6fca1"}, {file = "openai-1.24.0-py3-none-any.whl", hash = "sha256:81eed0d850a35a170797d15d94144eb993459411ba56325891ab488708f1b612"},
{file = "openai-1.23.6.tar.gz", hash = "sha256:612de2d54cf580920a1156273f84aada6b3dca26d048f62eb5364a4314d7f449"}, {file = "openai-1.24.0.tar.gz", hash = "sha256:9cc6ac92bac9d57c8d4bc101e9e4c7201304c88efb89320d0f0348625fa8647d"},
] ]
[package.dependencies] [package.dependencies]
@ -804,13 +804,13 @@ testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "no
[[package]] [[package]]
name = "pytest-asyncio" name = "pytest-asyncio"
version = "0.21.1" version = "0.21.2"
description = "Pytest support for asyncio" description = "Pytest support for asyncio"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "pytest-asyncio-0.21.1.tar.gz", hash = "sha256:40a7eae6dded22c7b604986855ea48400ab15b069ae38116e8c01238e9eeb64d"}, {file = "pytest_asyncio-0.21.2-py3-none-any.whl", hash = "sha256:ab664c88bb7998f711d8039cacd4884da6430886ae8bbd4eded552ed2004f16b"},
{file = "pytest_asyncio-0.21.1-py3-none-any.whl", hash = "sha256:8666c1c8ac02631d7c51ba282e0c69a8a452b211ffedf2599099845da5c5c37b"}, {file = "pytest_asyncio-0.21.2.tar.gz", hash = "sha256:d67738fc232b94b326b9d060750beb16e0074210b98dd8b58a5239fa2a154f45"},
] ]
[package.dependencies] [package.dependencies]
@ -928,104 +928,90 @@ files = [
[[package]] [[package]]
name = "regex" name = "regex"
version = "2024.4.16" version = "2024.4.28"
description = "Alternative regular expression module, to replace re." description = "Alternative regular expression module, to replace re."
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "regex-2024.4.16-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:fb83cc090eac63c006871fd24db5e30a1f282faa46328572661c0a24a2323a08"}, {file = "regex-2024.4.28-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cd196d056b40af073d95a2879678585f0b74ad35190fac04ca67954c582c6b61"},
{file = "regex-2024.4.16-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8c91e1763696c0eb66340c4df98623c2d4e77d0746b8f8f2bee2c6883fd1fe18"}, {file = "regex-2024.4.28-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8bb381f777351bd534462f63e1c6afb10a7caa9fa2a421ae22c26e796fe31b1f"},
{file = "regex-2024.4.16-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:10188fe732dec829c7acca7422cdd1bf57d853c7199d5a9e96bb4d40db239c73"}, {file = "regex-2024.4.28-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:47af45b6153522733aa6e92543938e97a70ce0900649ba626cf5aad290b737b6"},
{file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:956b58d692f235cfbf5b4f3abd6d99bf102f161ccfe20d2fd0904f51c72c4c66"}, {file = "regex-2024.4.28-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99d6a550425cc51c656331af0e2b1651e90eaaa23fb4acde577cf15068e2e20f"},
{file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a70b51f55fd954d1f194271695821dd62054d949efd6368d8be64edd37f55c86"}, {file = "regex-2024.4.28-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bf29304a8011feb58913c382902fde3395957a47645bf848eea695839aa101b7"},
{file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5c02fcd2bf45162280613d2e4a1ca3ac558ff921ae4e308ecb307650d3a6ee51"}, {file = "regex-2024.4.28-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:92da587eee39a52c91aebea8b850e4e4f095fe5928d415cb7ed656b3460ae79a"},
{file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c4ed75ea6892a56896d78f11006161eea52c45a14994794bcfa1654430984b22"}, {file = "regex-2024.4.28-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6277d426e2f31bdbacb377d17a7475e32b2d7d1f02faaecc48d8e370c6a3ff31"},
{file = "regex-2024.4.16-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bd727ad276bb91928879f3aa6396c9a1d34e5e180dce40578421a691eeb77f47"}, {file = "regex-2024.4.28-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:28e1f28d07220c0f3da0e8fcd5a115bbb53f8b55cecf9bec0c946eb9a059a94c"},
{file = "regex-2024.4.16-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7cbc5d9e8a1781e7be17da67b92580d6ce4dcef5819c1b1b89f49d9678cc278c"}, {file = "regex-2024.4.28-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:aaa179975a64790c1f2701ac562b5eeb733946eeb036b5bcca05c8d928a62f10"},
{file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:78fddb22b9ef810b63ef341c9fcf6455232d97cfe03938cbc29e2672c436670e"}, {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:6f435946b7bf7a1b438b4e6b149b947c837cb23c704e780c19ba3e6855dbbdd3"},
{file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:445ca8d3c5a01309633a0c9db57150312a181146315693273e35d936472df912"}, {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:19d6c11bf35a6ad077eb23852827f91c804eeb71ecb85db4ee1386825b9dc4db"},
{file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:95399831a206211d6bc40224af1c635cb8790ddd5c7493e0bd03b85711076a53"}, {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:fdae0120cddc839eb8e3c15faa8ad541cc6d906d3eb24d82fb041cfe2807bc1e"},
{file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:7731728b6568fc286d86745f27f07266de49603a6fdc4d19c87e8c247be452af"}, {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:e672cf9caaf669053121f1766d659a8813bd547edef6e009205378faf45c67b8"},
{file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4facc913e10bdba42ec0aee76d029aedda628161a7ce4116b16680a0413f658a"}, {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f57515750d07e14743db55d59759893fdb21d2668f39e549a7d6cad5d70f9fea"},
{file = "regex-2024.4.16-cp310-cp310-win32.whl", hash = "sha256:911742856ce98d879acbea33fcc03c1d8dc1106234c5e7d068932c945db209c0"}, {file = "regex-2024.4.28-cp310-cp310-win32.whl", hash = "sha256:a1409c4eccb6981c7baabc8888d3550df518add6e06fe74fa1d9312c1838652d"},
{file = "regex-2024.4.16-cp310-cp310-win_amd64.whl", hash = "sha256:e0a2df336d1135a0b3a67f3bbf78a75f69562c1199ed9935372b82215cddd6e2"}, {file = "regex-2024.4.28-cp310-cp310-win_amd64.whl", hash = "sha256:1f687a28640f763f23f8a9801fe9e1b37338bb1ca5d564ddd41619458f1f22d1"},
{file = "regex-2024.4.16-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:1210365faba7c2150451eb78ec5687871c796b0f1fa701bfd2a4a25420482d26"}, {file = "regex-2024.4.28-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:84077821c85f222362b72fdc44f7a3a13587a013a45cf14534df1cbbdc9a6796"},
{file = "regex-2024.4.16-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9ab40412f8cd6f615bfedea40c8bf0407d41bf83b96f6fc9ff34976d6b7037fd"}, {file = "regex-2024.4.28-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b45d4503de8f4f3dc02f1d28a9b039e5504a02cc18906cfe744c11def942e9eb"},
{file = "regex-2024.4.16-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:fd80d1280d473500d8086d104962a82d77bfbf2b118053824b7be28cd5a79ea5"}, {file = "regex-2024.4.28-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:457c2cd5a646dd4ed536c92b535d73548fb8e216ebee602aa9f48e068fc393f3"},
{file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7bb966fdd9217e53abf824f437a5a2d643a38d4fd5fd0ca711b9da683d452969"}, {file = "regex-2024.4.28-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2b51739ddfd013c6f657b55a508de8b9ea78b56d22b236052c3a85a675102dc6"},
{file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:20b7a68444f536365af42a75ccecb7ab41a896a04acf58432db9e206f4e525d6"}, {file = "regex-2024.4.28-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:459226445c7d7454981c4c0ce0ad1a72e1e751c3e417f305722bbcee6697e06a"},
{file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b74586dd0b039c62416034f811d7ee62810174bb70dffcca6439f5236249eb09"}, {file = "regex-2024.4.28-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:670fa596984b08a4a769491cbdf22350431970d0112e03d7e4eeaecaafcd0fec"},
{file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c8290b44d8b0af4e77048646c10c6e3aa583c1ca67f3b5ffb6e06cf0c6f0f89"}, {file = "regex-2024.4.28-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fe00f4fe11c8a521b173e6324d862ee7ee3412bf7107570c9b564fe1119b56fb"},
{file = "regex-2024.4.16-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f2d80a6749724b37853ece57988b39c4e79d2b5fe2869a86e8aeae3bbeef9eb0"}, {file = "regex-2024.4.28-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:36f392dc7763fe7924575475736bddf9ab9f7a66b920932d0ea50c2ded2f5636"},
{file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:3a1018e97aeb24e4f939afcd88211ace472ba566efc5bdf53fd8fd7f41fa7170"}, {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:23a412b7b1a7063f81a742463f38821097b6a37ce1e5b89dd8e871d14dbfd86b"},
{file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:8d015604ee6204e76569d2f44e5a210728fa917115bef0d102f4107e622b08d5"}, {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f1d6e4b7b2ae3a6a9df53efbf199e4bfcff0959dbdb5fd9ced34d4407348e39a"},
{file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:3d5ac5234fb5053850d79dd8eb1015cb0d7d9ed951fa37aa9e6249a19aa4f336"}, {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:499334ad139557de97cbc4347ee921c0e2b5e9c0f009859e74f3f77918339257"},
{file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:0a38d151e2cdd66d16dab550c22f9521ba79761423b87c01dae0a6e9add79c0d"}, {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:0940038bec2fe9e26b203d636c44d31dd8766abc1fe66262da6484bd82461ccf"},
{file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:159dc4e59a159cb8e4e8f8961eb1fa5d58f93cb1acd1701d8aff38d45e1a84a6"}, {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:66372c2a01782c5fe8e04bff4a2a0121a9897e19223d9eab30c54c50b2ebeb7f"},
{file = "regex-2024.4.16-cp311-cp311-win32.whl", hash = "sha256:ba2336d6548dee3117520545cfe44dc28a250aa091f8281d28804aa8d707d93d"}, {file = "regex-2024.4.28-cp311-cp311-win32.whl", hash = "sha256:c77d10ec3c1cf328b2f501ca32583625987ea0f23a0c2a49b37a39ee5c4c4630"},
{file = "regex-2024.4.16-cp311-cp311-win_amd64.whl", hash = "sha256:8f83b6fd3dc3ba94d2b22717f9c8b8512354fd95221ac661784df2769ea9bba9"}, {file = "regex-2024.4.28-cp311-cp311-win_amd64.whl", hash = "sha256:fc0916c4295c64d6890a46e02d4482bb5ccf33bf1a824c0eaa9e83b148291f90"},
{file = "regex-2024.4.16-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:80b696e8972b81edf0af2a259e1b2a4a661f818fae22e5fa4fa1a995fb4a40fd"}, {file = "regex-2024.4.28-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:08a1749f04fee2811c7617fdd46d2e46d09106fa8f475c884b65c01326eb15c5"},
{file = "regex-2024.4.16-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d61ae114d2a2311f61d90c2ef1358518e8f05eafda76eaf9c772a077e0b465ec"}, {file = "regex-2024.4.28-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b8eb28995771c087a73338f695a08c9abfdf723d185e57b97f6175c5051ff1ae"},
{file = "regex-2024.4.16-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8ba6745440b9a27336443b0c285d705ce73adb9ec90e2f2004c64d95ab5a7598"}, {file = "regex-2024.4.28-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:dd7ef715ccb8040954d44cfeff17e6b8e9f79c8019daae2fd30a8806ef5435c0"},
{file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6295004b2dd37b0835ea5c14a33e00e8cfa3c4add4d587b77287825f3418d310"}, {file = "regex-2024.4.28-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb0315a2b26fde4005a7c401707c5352df274460f2f85b209cf6024271373013"},
{file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4aba818dcc7263852aabb172ec27b71d2abca02a593b95fa79351b2774eb1d2b"}, {file = "regex-2024.4.28-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f2fc053228a6bd3a17a9b0a3f15c3ab3cf95727b00557e92e1cfe094b88cc662"},
{file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d0800631e565c47520aaa04ae38b96abc5196fe8b4aa9bd864445bd2b5848a7a"}, {file = "regex-2024.4.28-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7fe9739a686dc44733d52d6e4f7b9c77b285e49edf8570754b322bca6b85b4cc"},
{file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:08dea89f859c3df48a440dbdcd7b7155bc675f2fa2ec8c521d02dc69e877db70"}, {file = "regex-2024.4.28-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a74fcf77d979364f9b69fcf8200849ca29a374973dc193a7317698aa37d8b01c"},
{file = "regex-2024.4.16-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eeaa0b5328b785abc344acc6241cffde50dc394a0644a968add75fcefe15b9d4"}, {file = "regex-2024.4.28-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:965fd0cf4694d76f6564896b422724ec7b959ef927a7cb187fc6b3f4e4f59833"},
{file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:4e819a806420bc010489f4e741b3036071aba209f2e0989d4750b08b12a9343f"}, {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:2fef0b38c34ae675fcbb1b5db760d40c3fc3612cfa186e9e50df5782cac02bcd"},
{file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:c2d0e7cbb6341e830adcbfa2479fdeebbfbb328f11edd6b5675674e7a1e37730"}, {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bc365ce25f6c7c5ed70e4bc674f9137f52b7dd6a125037f9132a7be52b8a252f"},
{file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:91797b98f5e34b6a49f54be33f72e2fb658018ae532be2f79f7c63b4ae225145"}, {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:ac69b394764bb857429b031d29d9604842bc4cbfd964d764b1af1868eeebc4f0"},
{file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:d2da13568eff02b30fd54fccd1e042a70fe920d816616fda4bf54ec705668d81"}, {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:144a1fc54765f5c5c36d6d4b073299832aa1ec6a746a6452c3ee7b46b3d3b11d"},
{file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:370c68dc5570b394cbaadff50e64d705f64debed30573e5c313c360689b6aadc"}, {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:2630ca4e152c221072fd4a56d4622b5ada876f668ecd24d5ab62544ae6793ed6"},
{file = "regex-2024.4.16-cp312-cp312-win32.whl", hash = "sha256:904c883cf10a975b02ab3478bce652f0f5346a2c28d0a8521d97bb23c323cc8b"}, {file = "regex-2024.4.28-cp312-cp312-win32.whl", hash = "sha256:7f3502f03b4da52bbe8ba962621daa846f38489cae5c4a7b5d738f15f6443d17"},
{file = "regex-2024.4.16-cp312-cp312-win_amd64.whl", hash = "sha256:785c071c982dce54d44ea0b79cd6dfafddeccdd98cfa5f7b86ef69b381b457d9"}, {file = "regex-2024.4.28-cp312-cp312-win_amd64.whl", hash = "sha256:0dd3f69098511e71880fb00f5815db9ed0ef62c05775395968299cb400aeab82"},
{file = "regex-2024.4.16-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e2f142b45c6fed48166faeb4303b4b58c9fcd827da63f4cf0a123c3480ae11fb"}, {file = "regex-2024.4.28-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:374f690e1dd0dbdcddea4a5c9bdd97632cf656c69113f7cd6a361f2a67221cb6"},
{file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e87ab229332ceb127a165612d839ab87795972102cb9830e5f12b8c9a5c1b508"}, {file = "regex-2024.4.28-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:25f87ae6b96374db20f180eab083aafe419b194e96e4f282c40191e71980c666"},
{file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:81500ed5af2090b4a9157a59dbc89873a25c33db1bb9a8cf123837dcc9765047"}, {file = "regex-2024.4.28-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:5dbc1bcc7413eebe5f18196e22804a3be1bfdfc7e2afd415e12c068624d48247"},
{file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b340cccad138ecb363324aa26893963dcabb02bb25e440ebdf42e30963f1a4e0"}, {file = "regex-2024.4.28-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f85151ec5a232335f1be022b09fbbe459042ea1951d8a48fef251223fc67eee1"},
{file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c72608e70f053643437bd2be0608f7f1c46d4022e4104d76826f0839199347a"}, {file = "regex-2024.4.28-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:57ba112e5530530fd175ed550373eb263db4ca98b5f00694d73b18b9a02e7185"},
{file = "regex-2024.4.16-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a01fe2305e6232ef3e8f40bfc0f0f3a04def9aab514910fa4203bafbc0bb4682"}, {file = "regex-2024.4.28-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:224803b74aab56aa7be313f92a8d9911dcade37e5f167db62a738d0c85fdac4b"},
{file = "regex-2024.4.16-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:03576e3a423d19dda13e55598f0fd507b5d660d42c51b02df4e0d97824fdcae3"}, {file = "regex-2024.4.28-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0a54a047b607fd2d2d52a05e6ad294602f1e0dec2291152b745870afc47c1397"},
{file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:549c3584993772e25f02d0656ac48abdda73169fe347263948cf2b1cead622f3"}, {file = "regex-2024.4.28-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0a2a512d623f1f2d01d881513af9fc6a7c46e5cfffb7dc50c38ce959f9246c94"},
{file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:34422d5a69a60b7e9a07a690094e824b66f5ddc662a5fc600d65b7c174a05f04"}, {file = "regex-2024.4.28-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c06bf3f38f0707592898428636cbb75d0a846651b053a1cf748763e3063a6925"},
{file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:5f580c651a72b75c39e311343fe6875d6f58cf51c471a97f15a938d9fe4e0d37"}, {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:1031a5e7b048ee371ab3653aad3030ecfad6ee9ecdc85f0242c57751a05b0ac4"},
{file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:3399dd8a7495bbb2bacd59b84840eef9057826c664472e86c91d675d007137f5"}, {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:d7a353ebfa7154c871a35caca7bfd8f9e18666829a1dc187115b80e35a29393e"},
{file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8d1f86f3f4e2388aa3310b50694ac44daefbd1681def26b4519bd050a398dc5a"}, {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:7e76b9cfbf5ced1aca15a0e5b6f229344d9b3123439ffce552b11faab0114a02"},
{file = "regex-2024.4.16-cp37-cp37m-win32.whl", hash = "sha256:dd5acc0a7d38fdc7a3a6fd3ad14c880819008ecb3379626e56b163165162cc46"}, {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:5ce479ecc068bc2a74cb98dd8dba99e070d1b2f4a8371a7dfe631f85db70fe6e"},
{file = "regex-2024.4.16-cp37-cp37m-win_amd64.whl", hash = "sha256:ba8122e3bb94ecda29a8de4cf889f600171424ea586847aa92c334772d200331"}, {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:7d77b6f63f806578c604dca209280e4c54f0fa9a8128bb8d2cc5fb6f99da4150"},
{file = "regex-2024.4.16-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:743deffdf3b3481da32e8a96887e2aa945ec6685af1cfe2bcc292638c9ba2f48"}, {file = "regex-2024.4.28-cp38-cp38-win32.whl", hash = "sha256:d84308f097d7a513359757c69707ad339da799e53b7393819ec2ea36bc4beb58"},
{file = "regex-2024.4.16-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7571f19f4a3fd00af9341c7801d1ad1967fc9c3f5e62402683047e7166b9f2b4"}, {file = "regex-2024.4.28-cp38-cp38-win_amd64.whl", hash = "sha256:2cc1b87bba1dd1a898e664a31012725e48af826bf3971e786c53e32e02adae6c"},
{file = "regex-2024.4.16-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:df79012ebf6f4efb8d307b1328226aef24ca446b3ff8d0e30202d7ebcb977a8c"}, {file = "regex-2024.4.28-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7413167c507a768eafb5424413c5b2f515c606be5bb4ef8c5dee43925aa5718b"},
{file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e757d475953269fbf4b441207bb7dbdd1c43180711b6208e129b637792ac0b93"}, {file = "regex-2024.4.28-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:108e2dcf0b53a7c4ab8986842a8edcb8ab2e59919a74ff51c296772e8e74d0ae"},
{file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4313ab9bf6a81206c8ac28fdfcddc0435299dc88cad12cc6305fd0e78b81f9e4"}, {file = "regex-2024.4.28-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f1c5742c31ba7d72f2dedf7968998730664b45e38827637e0f04a2ac7de2f5f1"},
{file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d83c2bc678453646f1a18f8db1e927a2d3f4935031b9ad8a76e56760461105dd"}, {file = "regex-2024.4.28-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ecc6148228c9ae25ce403eade13a0961de1cb016bdb35c6eafd8e7b87ad028b1"},
{file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9df1bfef97db938469ef0a7354b2d591a2d438bc497b2c489471bec0e6baf7c4"}, {file = "regex-2024.4.28-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b7d893c8cf0e2429b823ef1a1d360a25950ed11f0e2a9df2b5198821832e1947"},
{file = "regex-2024.4.16-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62120ed0de69b3649cc68e2965376048793f466c5a6c4370fb27c16c1beac22d"}, {file = "regex-2024.4.28-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4290035b169578ffbbfa50d904d26bec16a94526071ebec3dadbebf67a26b25e"},
{file = "regex-2024.4.16-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c2ef6f7990b6e8758fe48ad08f7e2f66c8f11dc66e24093304b87cae9037bb4a"}, {file = "regex-2024.4.28-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:44a22ae1cfd82e4ffa2066eb3390777dc79468f866f0625261a93e44cdf6482b"},
{file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:8fc6976a3395fe4d1fbeb984adaa8ec652a1e12f36b56ec8c236e5117b585427"}, {file = "regex-2024.4.28-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fd24fd140b69f0b0bcc9165c397e9b2e89ecbeda83303abf2a072609f60239e2"},
{file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:03e68f44340528111067cecf12721c3df4811c67268b897fbe695c95f860ac42"}, {file = "regex-2024.4.28-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:39fb166d2196413bead229cd64a2ffd6ec78ebab83fff7d2701103cf9f4dfd26"},
{file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:ec7e0043b91115f427998febaa2beb82c82df708168b35ece3accb610b91fac1"}, {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:9301cc6db4d83d2c0719f7fcda37229691745168bf6ae849bea2e85fc769175d"},
{file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:c21fc21a4c7480479d12fd8e679b699f744f76bb05f53a1d14182b31f55aac76"}, {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:7c3d389e8d76a49923683123730c33e9553063d9041658f23897f0b396b2386f"},
{file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:12f6a3f2f58bb7344751919a1876ee1b976fe08b9ffccb4bbea66f26af6017b9"}, {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:99ef6289b62042500d581170d06e17f5353b111a15aa6b25b05b91c6886df8fc"},
{file = "regex-2024.4.16-cp38-cp38-win32.whl", hash = "sha256:479595a4fbe9ed8f8f72c59717e8cf222da2e4c07b6ae5b65411e6302af9708e"}, {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:b91d529b47798c016d4b4c1d06cc826ac40d196da54f0de3c519f5a297c5076a"},
{file = "regex-2024.4.16-cp38-cp38-win_amd64.whl", hash = "sha256:0534b034fba6101611968fae8e856c1698da97ce2efb5c2b895fc8b9e23a5834"}, {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:43548ad74ea50456e1c68d3c67fff3de64c6edb85bcd511d1136f9b5376fc9d1"},
{file = "regex-2024.4.16-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:a7ccdd1c4a3472a7533b0a7aa9ee34c9a2bef859ba86deec07aff2ad7e0c3b94"}, {file = "regex-2024.4.28-cp39-cp39-win32.whl", hash = "sha256:05d9b6578a22db7dedb4df81451f360395828b04f4513980b6bd7a1412c679cc"},
{file = "regex-2024.4.16-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6f2f017c5be19984fbbf55f8af6caba25e62c71293213f044da3ada7091a4455"}, {file = "regex-2024.4.28-cp39-cp39-win_amd64.whl", hash = "sha256:3986217ec830c2109875be740531feb8ddafe0dfa49767cdcd072ed7e8927962"},
{file = "regex-2024.4.16-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:803b8905b52de78b173d3c1e83df0efb929621e7b7c5766c0843704d5332682f"}, {file = "regex-2024.4.28.tar.gz", hash = "sha256:83ab366777ea45d58f72593adf35d36ca911ea8bd838483c1823b883a121b0e4"},
{file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:684008ec44ad275832a5a152f6e764bbe1914bea10968017b6feaecdad5736e0"},
{file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:65436dce9fdc0aeeb0a0effe0839cb3d6a05f45aa45a4d9f9c60989beca78b9c"},
{file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ea355eb43b11764cf799dda62c658c4d2fdb16af41f59bb1ccfec517b60bcb07"},
{file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98c1165f3809ce7774f05cb74e5408cd3aa93ee8573ae959a97a53db3ca3180d"},
{file = "regex-2024.4.16-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cccc79a9be9b64c881f18305a7c715ba199e471a3973faeb7ba84172abb3f317"},
{file = "regex-2024.4.16-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:00169caa125f35d1bca6045d65a662af0202704489fada95346cfa092ec23f39"},
{file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:6cc38067209354e16c5609b66285af17a2863a47585bcf75285cab33d4c3b8df"},
{file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:23cff1b267038501b179ccbbd74a821ac4a7192a1852d1d558e562b507d46013"},
{file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:b9d320b3bf82a39f248769fc7f188e00f93526cc0fe739cfa197868633d44701"},
{file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:89ec7f2c08937421bbbb8b48c54096fa4f88347946d4747021ad85f1b3021b3c"},
{file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4918fd5f8b43aa7ec031e0fef1ee02deb80b6afd49c85f0790be1dc4ce34cb50"},
{file = "regex-2024.4.16-cp39-cp39-win32.whl", hash = "sha256:684e52023aec43bdf0250e843e1fdd6febbe831bd9d52da72333fa201aaa2335"},
{file = "regex-2024.4.16-cp39-cp39-win_amd64.whl", hash = "sha256:e697e1c0238133589e00c244a8b676bc2cfc3ab4961318d902040d099fec7483"},
{file = "regex-2024.4.16.tar.gz", hash = "sha256:fa454d26f2e87ad661c4f0c5a5fe4cf6aab1e307d1b94f16ffdfcb089ba685c0"},
] ]
[[package]] [[package]]

11
libs/partners/upstage/tests/unit_tests/test_layout_analysis.py
View File

@ -17,7 +17,7 @@ MOCK_RESPONSE_JSON: Dict[str, Any] = {
{"x": 74, "y": 2338}, {"x": 74, "y": 2338},
], ],
"category": "header", "category": "header",
"html": "2021arXiv:2103.15348v2", "html": "<header id='0'>arXiv:2103.15348v2</header>",
"id": 0, "id": 0,
"page": 1, "page": 1,
"text": "arXiv:2103.15348v2", "text": "arXiv:2103.15348v2",
@ -30,7 +30,7 @@ MOCK_RESPONSE_JSON: Dict[str, Any] = {
{"x": 654, "y": 614}, {"x": 654, "y": 614},
], ],
"category": "paragraph", "category": "paragraph",
"html": "LayoutParser Toolkit", "html": "<p id='1'>LayoutParser Toolkit</p>",
"id": 1, "id": 1,
"page": 1, "page": 1,
"text": "LayoutParser Toolkit", "text": "LayoutParser Toolkit",
@ -59,6 +59,7 @@ def test_layout_analysis_param() -> None:
api_key="bar", api_key="bar",
output_type=output_type, output_type=output_type,
split=split, split=split,
exclude=[],
) )
assert loader.output_type == output_type assert loader.output_type == output_type
assert loader.split == split assert loader.split == split
@ -77,6 +78,7 @@ def test_none_split_text_output(mock_post: Mock) -> None:
output_type="text", output_type="text",
split="none", split="none",
api_key="valid_api_key", api_key="valid_api_key",
exclude=[],
) )
documents = loader.load() documents = loader.load()
@ -98,6 +100,7 @@ def test_element_split_text_output(mock_post: Mock) -> None:
output_type="text", output_type="text",
split="element", split="element",
api_key="valid_api_key", api_key="valid_api_key",
exclude=[],
) )
documents = loader.load() documents = loader.load()
@ -122,6 +125,7 @@ def test_page_split_text_output(mock_post: Mock) -> None:
output_type="text", output_type="text",
split="page", split="page",
api_key="valid_api_key", api_key="valid_api_key",
exclude=[],
) )
documents = loader.load() documents = loader.load()
@ -144,6 +148,7 @@ def test_none_split_html_output(mock_post: Mock) -> None:
output_type="html", output_type="html",
split="none", split="none",
api_key="valid_api_key", api_key="valid_api_key",
exclude=[],
) )
documents = loader.load() documents = loader.load()
@ -165,6 +170,7 @@ def test_element_split_html_output(mock_post: Mock) -> None:
output_type="html", output_type="html",
split="element", split="element",
api_key="valid_api_key", api_key="valid_api_key",
exclude=[],
) )
documents = loader.load() documents = loader.load()
@ -189,6 +195,7 @@ def test_page_split_html_output(mock_post: Mock) -> None:
output_type="html", output_type="html",
split="page", split="page",
api_key="valid_api_key", api_key="valid_api_key",
exclude=[],
) )
documents = loader.load() documents = loader.load()