fix: ignore escaped commas in CSV checks (#832)

* fix file content checking bug

* skip counting commas in quotes for csv detection

* add test for comma count

* change file content grab to -1

* version and changelog

* add csv to extension check

* add file to tests

* ingest-test-fixtures-update

* Update ingest test fixtures (#833)

Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>

* fix typo

* fix changelog wording

---------

Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>

CHANGELOG.md

@@ -10,6 +10,8 @@
 
 ### Fixes
 
+* CSV check now ignores escaped commas.
+* Fix for filetype exploration util when file content does not have a comma.
 * Adds negative lookahead to bullet pattern to avoid detecting plain text line
   breaks like `-------` as list items.
 * Fix pre tag parsing for `partition_html`

test_unstructured/file_utils/test_filetype.py

@@ -424,3 +424,15 @@ def test_detect_filetype_detects_empty_filename(filename="example-docs/empty.txt
 def test_detect_filetype_detects_empty_file(filename="example-docs/empty.txt"):
     with open(filename, "rb") as f:
         assert detect_filetype(file=f) == FileType.EMPTY
+
+
+def test_detect_filetype_skips_escape_commas_for_csv(tmpdir):
+    text = 'A,A,A,A,A\nA,A,A,"A,A",A\nA,A,A,"A,A",A'
+    filename = os.path.join(tmpdir.dirname, "csv-with-escaped-commas.csv")
+    with open(filename, "w") as f:
+        f.write(text)
+
+    assert detect_filetype(filename=filename) == FileType.CSV
+
+    with open(filename, "rb") as f:
+        assert detect_filetype(file=f) == FileType.CSV

test_unstructured_ingest/expected-structured-output/parameterized-ingest-output/example-docs/english-and-korean.png.json

@@ -27,13 +27,13 @@
     "text": "Note: Remember to write your own \"OPENING MESSAGE\" before you copy and paste the template. please always include [TREASURE HARUTO] for example:"
   },
   {
-    "type": "NarrativeText",
-    "element_id": "577b0ea5cd4f62a19b9d14dd0bd7272e",
+    "type": "UncategorizedText",
+    "element_id": "23a37aa2d5f39d5e2275dec011be76be",
     "metadata": {
       "data_source": {},
       "filetype": "image/png"
     },
-    "text": "안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 메 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 고 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다."
+    "text": "StS ofAl2, AS|E YGEAS 1B TREASUREMH HARUTOM| 2] BHEYLICH, BHO AY, HARUTO M BE = WSO Hol Wat SSGstsS LRU, O| Wil BS SH ASP ASS AZopO} HAS] TAI St a Bat FSAel GAS HS + U7/S HLICh."
   },
   {
     "type": "NarrativeText",
@@ -46,11 +46,11 @@
   },
   {
     "type": "NarrativeText",
-    "element_id": "da91cb5310386aafd5aaf6fd988b9616",
+    "element_id": "c37248b6d436997d36acc7852f502a8e",
     "metadata": {
       "data_source": {},
       "filetype": "image/png"
     },
-    "text": "4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]"
+    "text": "4. Use the hashtag of Haruto on your tweet to show that vou have sent your email]"
   }
 ]

unstructured/file_utils/exploration.py

@@ -61,7 +61,7 @@ def get_file_info_from_file_contents(
         data["filename"] = []
 
     for i, file_content in enumerate(file_contents):
-        _, content_string = file_content.split(",")
+        content_string = file_content.split(",")[-1]
         content_bytes = base64.b64decode(content_string)
         f = io.BytesIO(content_bytes)
         filetype = detect_filetype(file=f)

unstructured/file_utils/filetype.py

@@ -284,6 +284,9 @@ def detect_filetype(
             encoding = "utf-8"
         formatted_encoding = format_encoding_str(encoding)
 
+        if extension in [".eml", ".md", ".rtf", ".html", ".rst", ".org", ".csv", ".tsv", ".json"]:
+            return EXT_TO_FILETYPE.get(extension)
+
         # NOTE(crag): for older versions of the OS libmagic package, such as is currently
         # installed on the Unstructured docker image, .json files resolve to "text/plain"
         # rather than "application/json". this corrects for that case.
@@ -296,9 +299,6 @@ def detect_filetype(
         if file and _check_eml_from_buffer(file=file) is True:
             return FileType.EML
 
-        if extension in [".eml", ".md", ".rtf", ".html", ".rst", ".org", ".tsv", ".json"]:
-            return EXT_TO_FILETYPE.get(extension)
-
         # Safety catch
         if mime_type in STR_TO_FILETYPE:
             return STR_TO_FILETYPE[mime_type]
@@ -404,6 +404,13 @@ def _is_text_file_a_json(
     return re.match(LIST_OF_DICTS_PATTERN, file_text) is not None
 
 
+def _count_commas(text: str):
+    """Counts the number of commas in a line, excluding commas in quotes."""
+    pattern = r"(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$),"
+    matches = re.findall(pattern, text)
+    return len(matches)
+
+
 def _is_text_file_a_csv(
     filename: Optional[str] = None,
     file: Optional[IO] = None,
@@ -415,10 +422,10 @@ def _is_text_file_a_csv(
     if len(lines) < 2:
         return False
     lines = lines[: len(lines)] if len(lines) < 10 else lines[:10]
-    header = lines[0].split(",")
+    header_count = _count_commas(lines[0])
     if any("," not in line for line in lines):
         return False
-    return all(len(line.split(",")) == len(header) for line in lines[:-1])
+    return all(_count_commas(line) == header_count for line in lines[:1])
 
 
 def _check_eml_from_buffer(file: IO) -> bool: