fix: remove default encoding for ingest (#1036)

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.9.1-dev8
+## 0.9.1-dev9
 
 ### Enhancements
 
@@ -20,6 +20,7 @@
 * Pass `file_filename` metadata when partitioning file object
 * Skip ingest test on missing Slack token
 * Add Dropbox variables to CI environments
+* Remove default encoding for ingest
 * Adds new element type `EmailAddress` for recognising email address in the  text
 * Simplifies `min_partition` logic; makes partitions falling below the `min_partition`
   less likely.

test_unstructured_ingest/check-num-files-output.sh

@@ -12,9 +12,10 @@ EXPECTED_NUM_FILES=$1
 OUTPUT_FOLDER_NAME=$2
 SCRIPT_DIR=$(dirname "$(realpath "$0")")
 OUTPUT_DIR=$SCRIPT_DIR/structured-output/$OUTPUT_FOLDER_NAME
+num_files_created="$(find "$OUTPUT_DIR" -type f -exec printf '.' \; | wc -c | xargs)"
 
-if [[ "$(find "$OUTPUT_DIR" -type f -exec printf '.' \; | wc -c | xargs)" != "$EXPECTED_NUM_FILES" ]]; then
+if [[ num_files_created != "$EXPECTED_NUM_FILES" ]]; then
    echo
-   echo "$EXPECTED_NUM_FILES files should have been created."
+   echo "ERROR: $num_files_created files created. $EXPECTED_NUM_FILES files should have been created."
    exit 1
 fi

test_unstructured_ingest/expected-structured-output/azure/spring-weather.html.json

@@ -495,7 +495,7 @@
   },
   {
     "type": "NarrativeText",
-    "element_id": "f3be9748ecd68b20d706548129baa22d",
+    "element_id": "7480a79a5bad8a36f3f7e5d622f0b5f3",
     "metadata": {
       "data_source": {},
       "filetype": "text/html",
@@ -507,7 +507,7 @@
         }
       ]
     },
-    "text": "First, take steps to better prepare for the seasonal hazards weather can throw at you.\nThis could include a spring cleaning of your storm shelter or ensuring your emergency kit is fully stocked. Take a look at our infographics and social media posts to help you become “weather-ready.”"
+    "text": "First, take steps to better prepare for the seasonal hazards weather can throw at you.\r\nThis could include a spring cleaning of your storm shelter or ensuring your emergency kit is fully stocked. Take a look at our infographics and social media posts to help you become “weather-ready.”"
   },
   {
     "type": "NarrativeText",

test_unstructured_ingest/test-ingest-local.sh

@@ -17,4 +17,4 @@ PYTHONPATH=. ./unstructured/ingest/main.py \
     --file-glob "*.html" \
     --input-path example-docs
 
-sh "$SCRIPT_DIR"/check-num-files-output.sh 9 $OUTPUT_FOLDER_NAME
+sh "$SCRIPT_DIR"/check-num-files-output.sh 11 $OUTPUT_FOLDER_NAME

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.9.1-dev8"  # pragma: no cover
+__version__ = "0.9.1-dev9"  # pragma: no cover

unstructured/ingest/cli/common.py

@@ -201,8 +201,9 @@ def add_shared_options(cmd: Command):
         ),
         Option(
             ["--encoding"],
-            default="utf-8",
-            help="Text encoding to use when reading documents. Default: utf-8",
+            default=None,
+            help="Text encoding to use when reading documents. By default the encoding is "
+            "detected automatically.",
         ),
         Option(
             ["--api-key"],