mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-10-18 11:33:09 +00:00
89fa88f076
The current code assumes the first line of csv and tsv files are a
header line. Most csv and tsv files don't have a header line, and even
for those that do, dropping this line may not be the desired behavior.
Here is a snippet of code that demonstrates the current behavior and the
proposed fix
```
import pandas as pd
from lxml.html.soupparser import fromstring as soupparser_fromstring
c1 = """
Stanley Cups,,
Team,Location,Stanley Cups
Blues,STL,1
Flyers,PHI,2
Maple Leafs,TOR,13
"""
f = "./test.csv"
with open(f, 'w') as ff:
ff.write(c1)
print("Suggested Improvement Keep First Line")
table = pd.read_csv(f, header=None)
html_text = table.to_html(index=False, header=False, na_rep="")
text = soupparser_fromstring(html_text).text_content()
print(text)
print("\n\nOriginal Looses First Line")
table = pd.read_csv(f)
html_text = table.to_html(index=False, header=False, na_rep="")
text = soupparser_fromstring(html_text).text_content()
print(text)
```
---------
Co-authored-by: cragwolfe <crag@unstructured.io>
Co-authored-by: Yao You <theyaoyou@gmail.com>
Co-authored-by: Yao You <yao@unstructured.io>
49 lines
1.6 KiB
Bash
Executable File
49 lines
1.6 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
set -e
|
|
|
|
# Description: This test checks if all the processed content is the same as the expected outputs.
|
|
# Also checks if a large table can be ingested properly.
|
|
|
|
SCRIPT_DIR=$(dirname "$(realpath "$0")")
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
|
|
OUTPUT_FOLDER_NAME=airtable-diff
|
|
OUTPUT_DIR=$SCRIPT_DIR/structured-output/$OUTPUT_FOLDER_NAME
|
|
WORK_DIR=$SCRIPT_DIR/workdir/$OUTPUT_FOLDER_NAME
|
|
DOWNLOAD_DIR=$SCRIPT_DIR/download/$OUTPUT_FOLDER_NAME
|
|
CI=${CI:-"false"}
|
|
max_processes=${MAX_PROCESSES:=$(python3 -c "import os; print(os.cpu_count())")}
|
|
|
|
# shellcheck disable=SC1091
|
|
source "$SCRIPT_DIR"/cleanup.sh
|
|
function cleanup() {
|
|
cleanup_dir "$OUTPUT_DIR"
|
|
cleanup_dir "$WORK_DIR"
|
|
if [ "$CI" == "true" ]; then
|
|
cleanup_dir "$DOWNLOAD_DIR"
|
|
fi
|
|
}
|
|
trap cleanup EXIT
|
|
|
|
VARIED_DATA_BASE_ID="app5YQxSfp220fWtm"
|
|
VARIED_DATA_BASE_ID_2="appJ43QmP8I17zu88"
|
|
|
|
if [ -z "$AIRTABLE_PERSONAL_ACCESS_TOKEN" ]; then
|
|
echo "Skipping Airtable ingest test because the AIRTABLE_PERSONAL_ACCESS_TOKEN is not set."
|
|
exit 0
|
|
fi
|
|
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
airtable \
|
|
--download-dir "$DOWNLOAD_DIR" \
|
|
--personal-access-token "$AIRTABLE_PERSONAL_ACCESS_TOKEN" \
|
|
--list-of-paths "$VARIED_DATA_BASE_ID $VARIED_DATA_BASE_ID_2" \
|
|
--metadata-exclude filename,file_directory,metadata.data_source.date_processed,metadata.date,metadata.last_modified,metadata.detection_class_prob,metadata.parent_id,metadata.category_depth,metadatda.languages \
|
|
--num-processes "$max_processes" \
|
|
--preserve-downloads \
|
|
--reprocess \
|
|
--output-dir "$OUTPUT_DIR" \
|
|
--work-dir "$WORK_DIR"
|
|
|
|
"$SCRIPT_DIR"/check-diff-expected-output.sh $OUTPUT_FOLDER_NAME
|