-
Notifications
You must be signed in to change notification settings - Fork 817
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
expand fsspec downstream connectors (#1777)
### Description Replacing PR [1383](#1383) --------- Co-authored-by: Trevor Bossert <[email protected]> Co-authored-by: ryannikolaidis <[email protected]> Co-authored-by: rbiseck3 <[email protected]>
- Loading branch information
4 people
authored
Oct 30, 2023
1 parent
645a0fb
commit 680cfba
Showing
44 changed files
with
760 additions
and
129 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,3 +1,3 @@ | ||
| strategy average sample_sd population_sd count | ||
| cct-accuracy 0.777 0.088 0.072 3 | ||
| cct-%missing 0.087 0.045 0.037 3 | ||
| cct-accuracy 0.798 0.083 0.072 4 | ||
| cct-%missing 0.087 0.037 0.032 4 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,4 +1,4 @@ | ||
| filename connector cct-accuracy cct-%missing | ||
| science-exploration-1p.pptx box 0.861 0.09 | ||
| example-10k.html local 0.686 0.04 | ||
| IRS-form-1987.pdf azure 0.783 0.13 | ||
| IRS-form-1987.pdf azure 0.783 0.13 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,57 @@ | ||
| #!/usr/bin/env bash | ||
|
|
||
| set -e | ||
|
|
||
| SCRIPT_DIR=$(dirname "$(realpath "$0")") | ||
| cd "$SCRIPT_DIR"/.. || exit 1 | ||
| OUTPUT_FOLDER_NAME=azure-dest | ||
| OUTPUT_DIR=$SCRIPT_DIR/structured-output/$OUTPUT_FOLDER_NAME | ||
| WORK_DIR=$SCRIPT_DIR/workdir/$OUTPUT_FOLDER_NAME | ||
| max_processes=${MAX_PROCESSES:=$(python3 -c "import os; print(os.cpu_count())")} | ||
|
|
||
| if [ -z "$AZURE_DEST_CONNECTION_STR" ]; then | ||
| echo "Skipping Azure destination ingest test because the AZURE_DEST_CONNECTION_STR env var is not set." | ||
| exit 0 | ||
| fi | ||
|
|
||
| CONTAINER=utic-ingest-test-fixtures-output | ||
| DIRECTORY=$(date +%s) | ||
| REMOTE_URL="abfs://$CONTAINER/$DIRECTORY/" | ||
|
|
||
| # shellcheck disable=SC1091 | ||
| source "$SCRIPT_DIR"/cleanup.sh | ||
| function cleanup() { | ||
| cleanup_dir "$OUTPUT_DIR" | ||
| cleanup_dir "$WORK_DIR" | ||
|
|
||
| echo "deleting azure storage blob directory $CONTAINER/$DIRECTORY" | ||
| az storage fs directory delete -f "$CONTAINER" -n "$DIRECTORY" --connection-string "$AZURE_DEST_CONNECTION_STR" --yes | ||
|
|
||
| } | ||
| trap cleanup EXIT | ||
|
|
||
| # Create directory to use for testing | ||
| az storage fs directory create -f "$CONTAINER" --n "$DIRECTORY" --connection-string "$AZURE_DEST_CONNECTION_STR" | ||
|
|
||
| PYTHONPATH=. ./unstructured/ingest/main.py \ | ||
| local \ | ||
| --num-processes "$max_processes" \ | ||
| --metadata-exclude coordinates,filename,file_directory,metadata.data_source.date_processed,metadata.last_modified,metadata.detection_class_prob,metadata.parent_id,metadata.category_depth \ | ||
| --output-dir "$OUTPUT_DIR" \ | ||
| --strategy fast \ | ||
| --verbose \ | ||
| --reprocess \ | ||
| --input-path example-docs/fake-memo.pdf \ | ||
| --work-dir "$WORK_DIR" \ | ||
| azure \ | ||
| --overwrite \ | ||
| --remote-url "$REMOTE_URL" \ | ||
| --connection-string "$AZURE_DEST_CONNECTION_STR" | ||
|
|
||
| # Simply check the number of files uploaded | ||
| expected_num_files=1 | ||
| num_files_in_azure=$(az storage blob list -c "$CONTAINER" --prefix "$DIRECTORY"/example-docs/ --connection-string "$AZURE_DEST_CONNECTION_STR" | jq 'length') | ||
| if [ "$num_files_in_azure" -ne "$expected_num_files" ]; then | ||
| echo "Expected $expected_num_files files to be uploaded to azure, but found $num_files_in_azure files." | ||
| exit 1 | ||
| fi |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,54 @@ | ||
| #!/usr/bin/env bash | ||
| #TODO currently box api/sdk does not work to create folders and check for content similar to other fsspec ingest tests | ||
|
|
||
| # | ||
| #set -e | ||
| # | ||
| #SCRIPT_DIR=$(dirname "$(realpath "$0")") | ||
| #cd "$SCRIPT_DIR"/.. || exit 1 | ||
| #OUTPUT_FOLDER_NAME=box-dest | ||
| #OUTPUT_DIR=$SCRIPT_DIR/structured-output/$OUTPUT_FOLDER_NAME | ||
| #WORK_DIR=$SCRIPT_DIR/workdir/$OUTPUT_FOLDER_NAME | ||
| #max_processes=${MAX_PROCESSES:=$(python3 -c "import os; print(os.cpu_count())")} | ||
| #DESTINATION_BOX="box://utic-dev-tech-fixtures/utic-ingest-test-fixtures-output/$(date +%s)/" | ||
| # | ||
| #CI=${CI:-"false"} | ||
| # | ||
| #if [ -z "$BOX_APP_CONFIG" ] && [ -z "$BOX_APP_CONFIG_PATH" ]; then | ||
| # echo "Skipping Box ingest test because neither BOX_APP_CONFIG nor BOX_APP_CONFIG_PATH env vars are set." | ||
| # exit 0 | ||
| #fi | ||
| # | ||
| #if [ -z "$BOX_APP_CONFIG_PATH" ]; then | ||
| # # Create temporary service key file | ||
| # BOX_APP_CONFIG_PATH=$(mktemp) | ||
| # echo "$BOX_APP_CONFIG" >"$BOX_APP_CONFIG_PATH" | ||
| #fi | ||
| # | ||
| ## shellcheck disable=SC1091 | ||
| #source "$SCRIPT_DIR"/cleanup.sh | ||
| #function cleanup() { | ||
| # cleanup_dir "$OUTPUT_DIR" | ||
| # cleanup_dir "$WORK_DIR" | ||
| # if [ "$CI" == "true" ]; then | ||
| # cleanup_dir "$DOWNLOAD_DIR" | ||
| # fi | ||
| #} | ||
| #trap cleanup EXIT | ||
| # | ||
| #PYTHONPATH=. ./unstructured/ingest/main.py \ | ||
| # local \ | ||
| # --num-processes "$max_processes" \ | ||
| # --metadata-exclude coordinates,filename,file_directory,metadata.data_source.date_processed,metadata.last_modified,metadata.detection_class_prob,metadata.parent_id,metadata.category_depth \ | ||
| # --output-dir "$OUTPUT_DIR" \ | ||
| # --strategy fast \ | ||
| # --verbose \ | ||
| # --reprocess \ | ||
| # --input-path example-docs/fake-memo.pdf \ | ||
| # --work-dir "$WORK_DIR" \ | ||
| # box \ | ||
| # --box-app-config "$BOX_APP_CONFIG_PATH" \ | ||
| # --remote-url "$DESTINATION_BOX" \ | ||
| # | ||
| ## Simply check the number of files uploaded | ||
| #expected_num_files=1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,81 @@ | ||
| #!/usr/bin/env bash | ||
|
|
||
| set -e | ||
|
|
||
| SCRIPT_DIR=$(dirname "$(realpath "$0")") | ||
| cd "$SCRIPT_DIR"/.. || exit 1 | ||
| OUTPUT_FOLDER_NAME=dropbox-dest | ||
| OUTPUT_DIR=$SCRIPT_DIR/structured-output/$OUTPUT_FOLDER_NAME | ||
| WORK_DIR=$SCRIPT_DIR/workdir/$OUTPUT_FOLDER_NAME | ||
| max_processes=${MAX_PROCESSES:=$(python3 -c "import os; print(os.cpu_count())")} | ||
| DESTINATION_DROPBOX="/test-output/$(date +%s)" | ||
| CI=${CI:-"false"} | ||
|
|
||
| if [ -z "$DROPBOX_APP_KEY" ] || [ -z "$DROPBOX_APP_SECRET" ] || [ -z "$DROPBOX_REFRESH_TOKEN" ]; then | ||
| echo "Skipping Dropbox ingest test because one or more of these env vars is not set:" | ||
| echo "DROPBOX_APP_KEY, DROPBOX_APP_SECRET, DROPBOX_REFRESH_TOKEN" | ||
| exit 0 | ||
| fi | ||
|
|
||
| # Get a new access token from Dropbox | ||
| DROPBOX_RESPONSE=$(curl -s https://api.dropbox.com/oauth2/token -d refresh_token="$DROPBOX_REFRESH_TOKEN" -d grant_type=refresh_token -d client_id="$DROPBOX_APP_KEY" -d client_secret="$DROPBOX_APP_SECRET") | ||
| DROPBOX_ACCESS_TOKEN=$(jq -r '.access_token' <<< "$DROPBOX_RESPONSE") | ||
|
|
||
| # shellcheck disable=SC1091 | ||
| source "$SCRIPT_DIR"/cleanup.sh | ||
| function cleanup() { | ||
| cleanup_dir "$OUTPUT_DIR" | ||
| cleanup_dir "$WORK_DIR" | ||
| if [ "$CI" == "true" ]; then | ||
| cleanup_dir "$DOWNLOAD_DIR" | ||
| fi | ||
|
|
||
| echo "deleting test folder $DESTINATION_DROPBOX" | ||
| curl -X POST https://api.dropboxapi.com/2/files/delete_v2 \ | ||
| --header "Content-Type: application/json" \ | ||
| --header "Authorization: Bearer $DROPBOX_ACCESS_TOKEN" \ | ||
| --data "{\"path\":\"$DESTINATION_DROPBOX\"}" | jq | ||
| } | ||
| trap cleanup EXIT | ||
|
|
||
| # Create new folder for test | ||
| echo "creating temp directory in dropbox for testing: $DESTINATION_DROPBOX" | ||
| response=$(curl -X POST -s -w "\n%{http_code}" https://api.dropboxapi.com/2/files/create_folder_v2 \ | ||
| --header "Content-Type: application/json" \ | ||
| --header "Authorization: Bearer $DROPBOX_ACCESS_TOKEN" \ | ||
| --data "{\"autorename\":false,\"path\":\"$DESTINATION_DROPBOX\"}"); | ||
| http_code=$(tail -n1 <<< "$response") # get the last line | ||
| content=$(sed '$ d' <<< "$response") # get all but the last line which contains the status code | ||
|
|
||
| if [ "$http_code" -ge 300 ]; then | ||
| echo "Failed to create temp dir in dropbox: [$http_code] $content" | ||
| exit 1 | ||
| else | ||
| echo "$http_code:" | ||
| jq <<< "$content" | ||
| fi | ||
|
|
||
| PYTHONPATH=. ./unstructured/ingest/main.py \ | ||
| local \ | ||
| --num-processes "$max_processes" \ | ||
| --metadata-exclude coordinates,filename,file_directory,metadata.data_source.date_processed,metadata.last_modified,metadata.detection_class_prob,metadata.parent_id,metadata.category_depth \ | ||
| --output-dir "$OUTPUT_DIR" \ | ||
| --strategy fast \ | ||
| --verbose \ | ||
| --reprocess \ | ||
| --input-path example-docs/fake-memo.pdf \ | ||
| --work-dir "$WORK_DIR" \ | ||
| dropbox \ | ||
| --token "$DROPBOX_ACCESS_TOKEN" \ | ||
| --remote-url "dropbox://$DESTINATION_DROPBOX" \ | ||
|
|
||
| # Simply check the number of files uploaded | ||
| expected_num_files=1 | ||
| num_files_in_dropbox=$(curl -X POST https://api.dropboxapi.com/2/files/list_folder \ | ||
| --header "Content-Type: application/json" \ | ||
| --header "Authorization: Bearer $DROPBOX_ACCESS_TOKEN" \ | ||
| --data "{\"path\":\"$DESTINATION_DROPBOX/example-docs/\"}" | jq '.entries | length') | ||
| if [ "$num_files_in_dropbox" -ne "$expected_num_files" ]; then | ||
| echo "Expected $expected_num_files files to be uploaded to dropbox, but found $num_files_in_dropbox files." | ||
| exit 1 | ||
| fi |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.