Get rid off accents if file names - they will be normalized

piotrgredowski · Aug 22, 2023 · 582e47a · 582e47a
1 parent 328b33c
commit 582e47a
Show file tree

Hide file tree

Showing 5 changed files with 9 additions and 3 deletions.
diff --git a/bucket_of_utils/pdf/add_title_to_first_page.html b/bucket_of_utils/pdf/add_title_to_first_page.html
@@ -11,7 +11,7 @@
 
   <body>
     <py-config type="toml">
-      packages = ["pdf-annotate"]
+      packages = ["pdf-annotate", "unidecode"]
       [[fetch]]
       files = ["./add_title_to_first_page.py"]
     </py-config>
@@ -28,7 +28,7 @@ <h2>Config</h2>
         </div>
         <div class="col">
           <h2>Files</h2>
-            <input class="form-control" type="file" id="file-upload" multiple="multiple">
+            <input class="form-control" type="file" id="file-upload" multiple="multiple" accept="application/pdf">
             <div id="output_upload"></div>
             <div class="row align-items-start">
               <h2>Process</h2>

diff --git a/bucket_of_utils/pdf/index.py b/bucket_of_utils/pdf/index.py
@@ -13,6 +13,7 @@
 from js import window
 from pyodide.ffi import create_proxy
 from pyodide.ffi import to_js
+from unidecode import unidecode
 
 CONFIG_DISABLED = True
 
@@ -90,7 +91,9 @@ async def _process_files(*_, **__):
         reader = pdfrw.PdfReader(stream)
         doc = pdf_annotate.PdfAnnotator(reader)
 
-        converted = add_file_name_annotation_to_pdf(doc=doc, file_name=file_.name)
+        file_name = unidecode(file_.name)
+
+        converted = add_file_name_annotation_to_pdf(doc=doc, file_name=file_name)
         with tempfile.NamedTemporaryFile() as f:
             converted.write(f)
             f.seek(0)

diff --git a/pyproject.toml b/pyproject.toml
@@ -12,6 +12,7 @@ dependencies = [
     "shellingham>=1.5.0.post1",
     "pyodide-py>=0.23.4",
     "types-requests>=2.31.0.2",
+    "unidecode>=1.3.6",
 ]
 readme = "README.md"
 requires-python = ">= 3.11"

diff --git a/requirements-dev.lock b/requirements-dev.lock
@@ -47,6 +47,7 @@ typer==0.9.0
 types-requests==2.31.0.2
 types-urllib3==1.26.25.14
 typing-extensions==4.7.1
+unidecode==1.3.6
 urllib3==2.0.4
 virtualenv==20.24.2
 # The following packages are considered to be unsafe in a requirements file:

diff --git a/requirements.lock b/requirements.lock
@@ -28,4 +28,5 @@ typer==0.9.0
 types-requests==2.31.0.2
 types-urllib3==1.26.25.14
 typing-extensions==4.7.1
+unidecode==1.3.6
 urllib3==2.0.4