feat: check & validate supported formats #40

rueedlinger · Jun 13, 2024 · a86b21b · a86b21b
1 parent 3beb581
commit a86b21b
Show file tree

Hide file tree

Showing 8 changed files with 40 additions and 19 deletions.
diff --git a/teal/core/create.py b/teal/core/create.py
@@ -24,12 +24,23 @@
 class LibreOfficeAdapter:
     def __init__(self, libreoffice_cmd="soffice"):
         self.libreoffice_cmd = libreoffice_cmd
+        # at the moment restricted to these file endings
         self.supported_file_extensions = [
-            ".doc",
-            ".docx",
+            # OpenDocument Text
             ".odt",
+            # OpenDocument Text Template
+            ".ott",
+            # Rich Text Format
             ".rtf",
+            # Microsoft Word
+            ".doc",
+            # Microsoft Word XML
+            ".docx",
+            # Plain Text
             ".txt",
+            # Plain Text
+            ".text",
+            # PDF
             ".pdf",
         ]
 
@@ -45,7 +56,9 @@ async def create_pdf(
         if is_feature_enabled("TEAL_FEATURE_CREATE_PDF_CHECK_FILE_EXTENSION"):
             if file_ext not in self.supported_file_extensions:
                 return create_json_err_response(
-                    400, f"file extension '{file_ext}' is not supported ({filename})."
+                    400,
+                    f"file extension '{file_ext}' is not supported, supported "
+                    f"extensions are {sorted(self.supported_file_extensions)}.",
                 )
 
         # create tmp dir for all files
@@ -69,18 +82,19 @@ async def create_pdf(
             pdf_version = output_type.to_param()
 
         pages = parse_page_ranges(page_ranges)
-        _logger.debug(f"using pdf version {pdf_version}")
 
         # https://help.libreoffice.org/latest/en-US/text/shared/guide/pdf_params.html?&DbPAR=SHARED&System=UNIX
+        # https://help.libreoffice.org/latest/en-US/text/shared/guide/convertfilters.html?DbPAR=SHARED#bm_id541554406270299
+        # https://vmiklos.hu/blog/pdf-convert-to.html
         if pages is None:
             pdf_param = (
-                'pdf:draw_pdf_Export:{"SelectPdfVersion":{"type":"long","value":"'
+                'pdf:writer_pdf_Export:{"SelectPdfVersion":{"type":"long","value":"'
                 + pdf_version
                 + '"}}'
             )
         else:
             pdf_param = (
-                'pdf:draw_pdf_Export:{"SelectPdfVersion":{"type":"long","value":"'
+                'pdf:writer_pdf_Export:{"SelectPdfVersion":{"type":"long","value":"'
                 + pdf_version
                 + '"},"PageRange":{"type":"string","value":"'
                 + to_page_range(pages)

diff --git a/teal/core/extract.py b/teal/core/extract.py
@@ -44,7 +44,9 @@ async def extract_text(
         file_ext = get_file_ext(filename)
         if file_ext not in self.supported_file_extensions:
             return create_json_err_response(
-                400, f"file extension '{file_ext}' is not supported ({filename})."
+                400,
+                f"file extension '{file_ext}' is not supported, supported "
+                f"extensions are {sorted(self.supported_file_extensions)}.",
             )
 
         extracts = []
@@ -76,7 +78,9 @@ async def extract_text_with_ocr(
         file_ext = get_file_ext(filename)
         if file_ext not in self.supported_file_extensions:
             return create_json_err_response(
-                400, f"file extension '{file_ext}' is not supported ({filename})."
+                400,
+                f"file extension '{file_ext}' is not supported, supported "
+                f"extensions are {sorted(self.supported_file_extensions)}.",
             )
 
         extracts = []
@@ -125,7 +129,9 @@ async def extract_table(
         file_ext = get_file_ext(filename)
         if file_ext not in self.supported_file_extensions:
             return create_json_err_response(
-                400, f"file extension '{file_ext}' is not supported ({filename})."
+                400,
+                f"file extension '{file_ext}' is not supported, supported "
+                f"extensions are {sorted(self.supported_file_extensions)}.",
             )
 
         async with aiofiles.tempfile.NamedTemporaryFile(suffix=".pdf") as tmp_pdf_file:
@@ -193,7 +199,9 @@ async def extract_meta_data(
         file_ext = get_file_ext(filename)
         if file_ext not in self.supported_file_extensions:
             return create_json_err_response(
-                400, f"file extension '{file_ext}' is not supported ({filename})."
+                400,
+                f"file extension '{file_ext}' is not supported, supported "
+                f"extensions are {sorted(self.supported_file_extensions)}.",
             )
         meta_data = {}
         doc_info = {}

diff --git a/teal/core/ocr.py b/teal/core/ocr.py
@@ -40,7 +40,9 @@ async def create_pdf(
         file_ext = get_file_ext(filename)
         if file_ext not in self.supported_file_extensions:
             return create_json_err_response(
-                400, f"file extension '{file_ext}' is not supported ({filename})."
+                400,
+                f"file extension '{file_ext}' is not supported, supported "
+                f"extensions are {sorted(self.supported_file_extensions)}.",
             )
 
         # create tmp dir for all files

diff --git a/tests/test_api_create_pdf.py b/tests/test_api_create_pdf.py
@@ -1,4 +1,3 @@
-import os
 import tempfile
 
 import pytest
@@ -98,9 +97,7 @@ def test_create_pdf_wrong_file_type():
         response = client.post(url="/create/pdf", files={"file": tmp})
         assert response.status_code == 400
         assert response.json() == {
-            "message": "file extension '.xyz' is not supported ("
-            + os.path.basename(tmp.name)
-            + ")."
+            "message": "file extension '.xyz' is not supported, supported extensions are ['.doc', '.docx', '.odt', '.ott', '.pdf', '.rtf', '.text', '.txt']."
         }
 
 

diff --git a/tests/test_api_extract_meta.py b/tests/test_api_extract_meta.py
@@ -26,7 +26,7 @@ def test_pdf_extract_meta_wrong_file_ending():
         response = client.post(url="/extract/meta", files={"file": f})
         assert response.status_code == 400
         assert response.json() == {
-            "message": f"file extension '.docx' is not supported (word_document.docx)."
+            "message": f"file extension '.docx' is not supported, supported extensions are ['.pdf']."
         }
 
 

diff --git a/tests/test_api_extract_table.py b/tests/test_api_extract_table.py
@@ -115,7 +115,7 @@ def test_pdf_table_extract_with_wrong_file_ending():
         response = client.post(url="/extract/table", files={"file": f})
         assert response.status_code == 400
         assert response.json() == {
-            "message": f"file extension '.docx' is not supported (word_document.docx)."
+            "message": f"file extension '.docx' is not supported, supported extensions are ['.pdf']."
         }
 
 

diff --git a/tests/test_api_extract_text.py b/tests/test_api_extract_text.py
@@ -75,7 +75,7 @@ def test_extract_text_with_wrong_file_ending():
         response = client.post(url="/extract/text", files={"file": f})
         assert response.status_code == 400
         assert response.json() == {
-            "message": f"file extension '.docx' is not supported (word_document.docx)."
+            "message": f"file extension '.docx' is not supported, supported extensions are ['.pdf']."
         }
 
 

diff --git a/tests/test_api_ocr_pdf.py b/tests/test_api_ocr_pdf.py
@@ -175,7 +175,7 @@ def test_ocr_pdf_with_wrong_file_ending():
         response = client.post(url="/ocr/pdf", files={"file": f})
         assert response.status_code == 400
         assert response.json() == {
-            "message": f"file extension '.docx' is not supported (word_document.docx)."
+            "message": f"file extension '.docx' is not supported, supported extensions are ['.pdf']."
         }