Add copyright notice

Marcin Kardas · Marcin Kardas · commit 0be43a9d1c6f · 2020-04-28T15:30:31.000+01:00
diff --git a/axcell/__init__.py b/axcell/__init__.py
@@ -0,0 +1,2 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
diff --git a/axcell/config.py b/axcell/config.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import logging
 from pathlib import Path
 
diff --git a/axcell/data/__init__.py b/axcell/data/__init__.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import logging
 from .. import config # to get logging init
 
@@ -7,4 +9,4 @@
     from db import *
 except:
     logger.info("Unable to intialise django falling back to json data")
-    from json import *
+    from json import *
diff --git a/axcell/data/db.py b/axcell/data/db.py
@@ -1 +1,3 @@
-raise NotImplementedError()
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
+raise NotImplementedError()
diff --git a/axcell/data/doc_utils.py b/axcell/data/doc_utils.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 from bs4 import BeautifulSoup, Comment, Tag, NavigableString
 import codecs
diff --git a/axcell/data/elastic.py b/axcell/data/elastic.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from bs4 import BeautifulSoup
 import pandas as pd
 import re
diff --git a/axcell/data/json.py b/axcell/data/json.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 #%%
 import json
 import re
diff --git a/axcell/data/paper_collection.py b/axcell/data/paper_collection.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from .elastic import Paper as PaperText, Fragments
 from .table import Table, read_tables
 from .json import load_gql_dump
diff --git a/axcell/data/references.py b/axcell/data/references.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 # Open source tools lfoppiano/grobid
 from collections import OrderedDict, Counter, Iterable, defaultdict
 from dataclasses import dataclass, field
diff --git a/axcell/data/structure.py b/axcell/data/structure.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 import pandas as pd
 from collections import namedtuple
diff --git a/axcell/data/table.py b/axcell/data/table.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import pandas as pd
 import numpy as np
 import json
diff --git a/axcell/errors.py b/axcell/errors.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 class PipelineError(Exception):
     pass
 
diff --git a/axcell/helpers/__init__.py b/axcell/helpers/__init__.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from .latex_converter import LatexConverter
 from .unpack import Unpack
 
diff --git a/axcell/helpers/cache.py b/axcell/helpers/cache.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import pandas as pd
 import json
 from collections import defaultdict
diff --git a/axcell/helpers/explainers.py b/axcell/helpers/explainers.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from axcell.models.linking.metrics import Metrics
 from ..models.structure import TableType
 from ..loggers import StructurePredictionEvaluator, LinkerEvaluator, FilteringEvaluator
diff --git a/axcell/helpers/interpret.py b/axcell/helpers/interpret.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from fastai.text.interpret import TextClassificationInterpretation as AbsTextClassificationInterpretation, _eval_dropouts
 from fastai.basic_data import DatasetType
 import torch
diff --git a/axcell/helpers/jupyter.py b/axcell/helpers/jupyter.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from IPython.core.display import display, HTML
 from .table_style import table_style
 import numpy as np
diff --git a/axcell/helpers/latex_converter.py b/axcell/helpers/latex_converter.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import docker
 from docker.errors import ContainerError, ImageNotFound
 from pathlib import Path
diff --git a/axcell/helpers/optimize.py b/axcell/helpers/optimize.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import pandas as pd, numpy as np
 from dataclasses import dataclass, replace
 from axcell.models.linking.metrics import CM
diff --git a/axcell/helpers/reannotate.py b/axcell/helpers/reannotate.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import requests
 from axcell import config
 from axcell.data.paper_collection import _load_annotated_papers
diff --git a/axcell/helpers/table_style.py b/axcell/helpers/table_style.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 table_style="""<style>
 body{margin:0;padding:0;font-family:-apple-system,BlinkMacSystemFont,Segoe UI,Roboto,Oxygen,Ubuntu,Cantarell,Fira Sans,Droid Sans,Helvetica Neue,sans-serif;-webkit-font-smoothing:antialiased;-moz-osx-font-smoothing:grayscale}code{font-family:source-code-pro,Menlo,Monaco,Consolas,Courier New,monospace}.tableWrapper{-overflow:auto}.tableWrapper .has-annotations{color:#ff3860}.tableWrapper .model-params{background-color:#209cee;color:rgba(0,0,0,.7)}.tableWrapper .table-meta{background-color:#fff3c5;color:rgba(0,0,0,.7)}.tableWrapper .model-best{background-color:#ff3860;color:rgba(0,0,0,.7)}.tableWrapper .model-competing{background-color:#ffdd57;color:rgba(0,0,0,.7)}.tableWrapper .model-paper{background-color:#ff3860;color:#fff}.tableWrapper .dataset-sub{background-color:#23d160;color:#fff}.tableWrapper .dataset-metric{background-color:#209cee;color:#fff}.tableWrapper .dataset{background-color:#02bd43;color:#fff}.tableWrapper .trash{background-color:#363636;color:#f5f5f5}.tableWrapper .wtf{background-color:#f0f;color:#f5f5f5}.tableWrapper .dataset-task{background-color:#77ecdd;color:rgba(0,0,0,.7)}.tableWrapper .dataset-paper{background-color:#e4ffee;color:rgba(0,0,0,.7)}.tableWrapper td.focused-cell{outline:2px solid #9ecaed;border-radius:7px;box-shadow:0 0 10px #9ecaed}.tableWrapper span.text-bold{font-weight:700}.tableWrapper span.text-italic{font-style:italic}.tableWrapper span.text-red{color:red}.tableWrapper span.text-green{color:green}.tableWrapper span.text-blue{color:#00f}.predict-dataset,.predict-dataset-metric,.predict-model-competing,.predict-model-paper,.predict-model-params,.predict-table-meta{outline:2px solid #9ecaed;border-radius:7px;box-shadow:0 0 10px #9ecaed}.tableWrapper .predict-model-params{background-color:#209cee;color:rgba(0,0,0,.7)}.tableWrapper .predict-table-meta{background-color:#fff3c5;color:rgba(0,0,0,.7)}.tableWrapper .predict-model-competing{background-color:#ffdd57;color:rgba(0,0,0,.7)}.tableWrapper .predict-model-paper{background-color:#ff3860;color:#fff}.tableWrapper .predict-dataset-metric{background-color:#209cee;color:#fff}.tableWrapper .predict-dataset{background-color:#02bd43;color:#fff}.tableWrapper td{border:inherit}.tableWrapper table tr td.border-l{border-left:1px solid #000}.tableWrapper table tr td.border-r{border-right:1px solid #000}.tableWrapper table tr td.border-t{border-top:1px solid #000}.tableWrapper table tr td.border-b{border-bottom:1px solid #000}.tableWrapper table tr td.border-ll{border-left:2px solid #000}.tableWrapper table tr td.border-rr{border-right:2px solid #000}.tableWrapper table tr td.border-tt{border-top:2px solid #000}.tableWrapper table tr td.border-bb{border-bottom:2px solid #000}.tableWrapper table tr td.align-left{text-align:left}.tableWrapper table tr td.align-right{text-align:right}.tableWrapper table tr td.align-center{text-align:center}.tableWrapper table tr td.align-justify{text-align:justify}div.form-group>input.form-control.input-sm{border-radius:2px;font-size:.75rem;background-color:#fff;color:#363636;box-shadow:inset 0 1px 2px rgba(10,10,10,.1);max-width:100%;width:100%;height:2.25em;padding:calc(.375em - 1px) calc(.625em - 1px);position:relative;border:1px solid #b5b5b5}div.form-group>input.form-control.input-sm:focus{border-color:#3273dc;box-shadow:0 0 0 .125em rgba(50,115,220,.25)}.ht_clone_top{z-index:20}.evaluation-tables{overflow:scroll;max-height:20vh;border-top:1px solid #a9a9a9}.navbar.is-fixed-bottom,.navbar.is-fixed-top{z-index:200}body{padding-bottom:20vh}
 .tableWrapper .final-proposal{ background: lightgreen }
diff --git a/axcell/helpers/training.py b/axcell/helpers/training.py
@@ -1,4 +1,6 @@
 
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 def set_seed(seed, name, quiet=False, all_gpus=True):
     import torch
     import numpy as np
@@ -11,4 +13,4 @@ def set_seed(seed, name, quiet=False, all_gpus=True):
     np.random.seed(seed)
     random.seed(seed)
     if all_gpus:
-        torch.cuda.manual_seed_all(seed)
+        torch.cuda.manual_seed_all(seed)
diff --git a/axcell/helpers/unpack.py b/axcell/helpers/unpack.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from magic import Magic
 import tarfile
 import gzip
diff --git a/axcell/loggers.py b/axcell/loggers.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import sys
 import pandas as pd
 from .models.structure.experiment import Experiment, label_map, Labels
diff --git a/axcell/mocks/latex_converter.py b/axcell/mocks/latex_converter.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 class LatexConverterMock:
     def __init__(self, mock_file):
         with open(mock_file, "r") as f:
diff --git a/axcell/models/linking/__init__.py b/axcell/models/linking/__init__.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from .taxonomy import Taxonomy
 from .linker import Linker
 from .context_search import ContextSearch, DatasetExtractor, EvidenceFinder
diff --git a/axcell/models/linking/acronym_extractor.py b/axcell/models/linking/acronym_extractor.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import spacy
 from scispacy.abbreviation import AbbreviationDetector
 from .utils import normalize_cell, normalize_dataset
diff --git a/axcell/models/linking/bm25_naive.py b/axcell/models/linking/bm25_naive.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 from decimal import Decimal, localcontext, InvalidOperation
 from dataclasses import dataclass
diff --git a/axcell/models/linking/context_search.py b/axcell/models/linking/context_search.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 # metrics[taxonomy name] is a list of normalized evidences for taxonomy name
 from collections import Counter
 
diff --git a/axcell/models/linking/execution.py b/axcell/models/linking/execution.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import pandas as pd
 from django.db import connection
 from IPython.core.display import display
diff --git a/axcell/models/linking/extractors.py b/axcell/models/linking/extractors.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 
 dataset_name_re = re.compile(r"\b(the)\b\s*(?P<name>((?!(the)\b)\w+\W+){1,10}?)(test|val(\.|idation)?|dev(\.|elopment)?|train(\.|ing)?\s+)?\bdata\s*set\b", re.IGNORECASE)
diff --git a/axcell/models/linking/format.py b/axcell/models/linking/format.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 from decimal import Decimal, ROUND_DOWN, ROUND_HALF_UP, InvalidOperation
 
diff --git a/axcell/models/linking/linker.py b/axcell/models/linking/linker.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from .bm25_naive import linked_proposals
 from ...pipeline_logger import pipeline_logger
 
diff --git a/axcell/models/linking/manual_dicts.py b/axcell/models/linking/manual_dicts.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 metrics = {
     'Accuracy': ['acc', 'accuracy'],
     'BLEU': ['bleu'],
diff --git a/axcell/models/linking/metrics.py b/axcell/models/linking/metrics.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from fastai.text import *
 from sklearn.metrics import confusion_matrix
 import seaborn as sn
diff --git a/axcell/models/linking/probs.py b/axcell/models/linking/probs.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from collections import Counter
 
 
diff --git a/axcell/models/linking/proposals_filters.py b/axcell/models/linking/proposals_filters.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from ...pipeline_logger import pipeline_logger
 import pandas as pd
 from enum import Enum
diff --git a/axcell/models/linking/taxonomy.py b/axcell/models/linking/taxonomy.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from pathlib import Path
 import json
 from collections import OrderedDict
diff --git a/axcell/models/linking/utils.py b/axcell/models/linking/utils.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from unidecode import unidecode
 import re
 
diff --git a/axcell/models/structure/__init__.py b/axcell/models/structure/__init__.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 import numpy as np
 import pandas as pd
diff --git a/axcell/models/structure/experiment.py b/axcell/models/structure/experiment.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import dataclasses
 from dataclasses import dataclass
 import json
diff --git a/axcell/models/structure/nbsvm.py b/axcell/models/structure/nbsvm.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 import string
 from fastai.text import *  # just for utilty functions pd, np, Path etc.
diff --git a/axcell/models/structure/structure_predictor.py b/axcell/models/structure/structure_predictor.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from fastai.text import *
 from pathlib import Path
 import pandas as pd
diff --git a/axcell/models/structure/transfo_experiment.py b/axcell/models/structure/transfo_experiment.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import time
 
 from .experiment import Experiment
diff --git a/axcell/models/structure/type_predictor.py b/axcell/models/structure/type_predictor.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from fastai.text import *
 from pathlib import Path
 import pandas as pd
diff --git a/axcell/models/structure/ulmfit.py b/axcell/models/structure/ulmfit.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from fastai.text import *
 from pathlib import Path
 
diff --git a/axcell/models/structure/ulmfit_experiment.py b/axcell/models/structure/ulmfit_experiment.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from .experiment import Experiment, label_map_ext
 from axcell.models.structure.nbsvm import *
 from sklearn.metrics import confusion_matrix
diff --git a/axcell/pipeline_logger.py b/axcell/pipeline_logger.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 
 
diff --git a/axcell/tests/test_metric_ranges.py b/axcell/tests/test_metric_ranges.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import pytest
 from decimal import Decimal
 from axcell.models.linking.bm25_naive import convert_metric
diff --git a/clean_html.sh b/clean_html.sh
@@ -1,4 +1,7 @@
 #!/usr/bin/env bash
+
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 SOURCE=$(realpath "$1")
 [ ! -f "$SOURCE" ] && echo "File $SOURCE not found." >&2 && exit 1
 mkdir -p $(dirname "$2")
diff --git a/docker-latex2html.sh b/docker-latex2html.sh
@@ -1,4 +1,7 @@
 #!/usr/bin/env bash
+
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 SOURCE_DIR=$(realpath "$1") 	#~/arxiv/unpacked/1701/1701.xyz
 [ ! -d "$SOURCE_DIR" ] && echo "Directory $SOURCE_DIR not found." >&2 && exit 1
 mkdir -p $(dirname "$2")
diff --git a/download_arxiv_ml_papers.sh b/download_arxiv_ml_papers.sh
@@ -1,4 +1,7 @@
 #!/bin/bash
+
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 index_dir="index"
 papers_dir="papers"
 src_dir="src"
diff --git a/extract_tables.py b/extract_tables.py
@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import sys
 from bs4 import BeautifulSoup, Comment, NavigableString
 import fire
diff --git a/extract_texts.py b/extract_texts.py
@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import fire
 from axcell.data.elastic import Paper
 from pathlib import Path
diff --git a/flatten_evaltab.sh b/flatten_evaltab.sh
@@ -1,2 +1,5 @@
 #!/usr/bin/env bash
+
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 jq -c '.. | select(.datasets?) | .task as $task | .datasets | .[] | .dataset as $dataset | .sota.rows[] | {paper_url, paper_title, model_name} as $paper | .metrics | . as $metrics | keys[] | {dataset: $dataset, metric_name: ., metric_value: $metrics[.], paper_url: $paper.paper_url, paper_title: $paper.paper_title, model_name: $paper.model_name, task: $task }' "$1" | grep arxiv\.org | jq -s '.'
diff --git a/get_papers_links.sh b/get_papers_links.sh
@@ -1,2 +1,5 @@
 #!/usr/bin/env bash
+
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 jq '.. | select(.sota?) | .sota.rows[] | .paper_url' "$1" | grep arxiv | sed -e 's#"##g' -e 's#http:#https:#' | sort -u
diff --git a/guess_main.py b/guess_main.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from pathlib import Path
 import re
 import sys
diff --git a/helpers.py b/helpers.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 from fire import Fire
 from pathlib import Path
 from axcell.data.paper_collection import PaperCollection
diff --git a/init_references.py b/init_references.py
@@ -1,3 +1,5 @@
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import re
 import json
 from pathlib import Path
diff --git a/label_tables.py b/label_tables.py
@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import fire
 from sota_extractor.taskdb import TaskDB
 from pathlib import Path
diff --git a/latex2html.sh b/latex2html.sh
@@ -1,4 +1,7 @@
 #!/usr/bin/env bash
+
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 OUTNAME="$1"
 echo $OUTNAME
 RO_SOURCE_DIR="${2:-/files/ro-source}"
diff --git a/normalize_metrics.py b/normalize_metrics.py
@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+#  Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
+
 import fire
 from label_tables import get_sota_tasks
 
diff --git a/normalize_references.py b/normalize_references.py
diff --git a/parse_references.py b/parse_references.py
diff --git a/setup.py b/setup.py
diff --git a/tables2json.py b/tables2json.py
diff --git a/unpack-sources.sh b/unpack-sources.sh

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved`
	`2`	`+`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved`
	`2`	`+`
`1`	`3`	`import logging`
`2`	`4`	`from pathlib import Path`
`3`	`5`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved`
	`2`	`+`
`1`	`3`	`import re`
`2`	`4`	`from bs4 import BeautifulSoup, Comment, Tag, NavigableString`
`3`	`5`	`import codecs`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved`
	`2`	`+`
`1`	`3`	`from bs4 import BeautifulSoup`
`2`	`4`	`import pandas as pd`
`3`	`5`	`import re`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved`
	`2`	`+`
`1`	`3`	`#%%`
`2`	`4`	`import json`
`3`	`5`	`import re`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved`
	`2`	`+`
`1`	`3`	`from .elastic import Paper as PaperText, Fragments`
`2`	`4`	`from .table import Table, read_tables`
`3`	`5`	`from .json import load_gql_dump`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved`
	`2`	`+`
`1`	`3`	`# Open source tools lfoppiano/grobid`
`2`	`4`	`from collections import OrderedDict, Counter, Iterable, defaultdict`
`3`	`5`	`from dataclasses import dataclass, field`