Merge pull request #31 from openscilab/feature/pptx

add support for .pptx, .xlsx format

CHANGELOG.md

@@ -6,18 +6,27 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ## [Unreleased]
 ### Added
+- `pptx` and `xlsx` support
+- `get_microsoft_format` function in `util.py`
 ### Changed
+- `extract` function in `util.py`
+- `remove_format` function in `util.py`
+- `clear` function in `functions.py`
+- `clear_all` function in `functions.py`
+- `update` function in `functions.py`
+- `update_all` function in `functions.py`
+- `extract_namespaces` function in `util.py`
 ## [0.1] - 2024-06-19
 ### Added
 - `CLI` handler
 - `main` function in `__main__.py`
 - `README.md`
-- `clear` function `functions.py`
+- `clear` function in `functions.py`
 - `clear_all` function in `functions.py`
-- `update` function `functions.py`
-- `update_all` function `functions.py`
-- `run_dmeta` function `functions.py`
-- `dmeta_help` function `functions.py`
+- `update` function in `functions.py`
+- `update_all` function in `functions.py`
+- `run_dmeta` function in `functions.py`
+- `dmeta_help` function in `functions.py`
 - `extract_namespaces` function in `util.py`
 - `remove_format` function in `util.py`
 - `extract_docx` function in `util.py`

README.md

@@ -144,7 +144,10 @@ dmeta --update-all --config "./config.json"
 ## Supported files
 | File format | support | 
 | ---------------- | ---------------- | 
-| Microsoft word office(.docx) | ✅ | 
+| Microsoft Word (.docx) | ✅ |
+| Microsoft PowerPoint (.pptx) | ✅ |
+| Microsoft Excel (.xlsx) | ✅ |
+
 
 ## Issues & bug reports
 

dev-requirements.txt

@@ -1,5 +1,6 @@
 art==6.2
 defusedxml==0.7.1
+lxml>=5.2.2
 setuptools>=40.8.0
 vulture>=1.0
 bandit>=1.5.1

dmeta/functions.py

@@ -4,75 +4,75 @@
 import shutil
 import zipfile
 from art import tprint
-from .util import remove_format, extract_docx, read_json
-import defusedxml.ElementTree as ET
+from .util import get_microsoft_format, extract, read_json
+import defusedxml.lxml as lxml
+
+
 from .params import CORE_XML_MAP, APP_XML_MAP, OVERVIEW, DMETA_VERSION
 
 
-def clear(docx_file_name):
+def clear(microsoft_file_name):
     """
-    Clear all the editable metadata in the given .docx file.
+    Clear all the editable metadata in the given microsoft file.
 
-    :param docx_file_name: name of .docx file
-    :type docx_file_name: str
+    :param microsoft_file_name: name of microsoft file
+    :type microsoft_file_name: str
     :return: None
     """
-    docx_file_name = remove_format(docx_file_name)
-    unzipped_dir, source_file = extract_docx(docx_file_name)
+    microsoft_format = get_microsoft_format(microsoft_file_name)
+    unzipped_dir, source_file = extract(microsoft_file_name)
     doc_props_dir = os.path.join(unzipped_dir, "docProps")
     core_xml_path = os.path.join(doc_props_dir, "core.xml")
     app_xml_path = os.path.join(doc_props_dir, "app.xml")
 
     if os.path.exists(core_xml_path):
-        e_core = ET.parse(core_xml_path)
+        e_core = lxml.parse(core_xml_path)
         for xml_element in e_core.iter():
-            for personal_field in CORE_XML_MAP.keys():
-                associated_xml_tag = CORE_XML_MAP[personal_field]
-                if (associated_xml_tag in xml_element.tag):
+            for personal_field in CORE_XML_MAP.values():
+                if (personal_field in xml_element.tag):
                     xml_element.text = ""
-        e_core.write(core_xml_path, "utf-8", True, None, "xml")
+        e_core.write(core_xml_path)
 
     if os.path.exists(app_xml_path):
-        e_app = ET.parse(app_xml_path)
+        e_app = lxml.parse(app_xml_path)
         for xml_element in e_app.iter():
-            for personal_field in APP_XML_MAP.keys():
-                associated_xml_tag = APP_XML_MAP[personal_field]
-                if (associated_xml_tag in xml_element.tag):
+            for personal_field in APP_XML_MAP.values():
+                if (personal_field in xml_element.tag):
                     xml_element.text = ""
-        e_app.write(app_xml_path, "utf-8", True, None, "xml")
+        e_app.write(app_xml_path)
 
-    modified_docx = docx_file_name + "_cleared"
-    with zipfile.ZipFile(modified_docx + ".docx", "w") as docx:
+    modified = microsoft_file_name[:microsoft_file_name.rfind('.')] + "_cleared"
+    with zipfile.ZipFile(modified + "." + microsoft_format, "w") as file:
         for file_name in source_file.namelist():
-            docx.write(os.path.join(unzipped_dir, file_name), file_name)
-        docx.close()
+            file.write(os.path.join(unzipped_dir, file_name), file_name)
+        file.close()
     shutil.rmtree(unzipped_dir)
 
 
 def clear_all():
     """
-    Clear all the editable metadata in any .docx file in the current directory.
+    Clear all the editable metadata in any microsoft file in the current directory.
 
     :return: None
     """
     path = os.getcwd()
     dir_list = os.listdir(path)
-    docx_files = []
+    microsoft_files = []
     for item in dir_list:
-        if ".docx" in item:
-            docx_files.append(item)
-    for docx_file in docx_files:
-        clear(docx_file)
+        if get_microsoft_format(item) is not None:
+            microsoft_files.append(item)
+    for microsoft_file in microsoft_files:
+        clear(microsoft_file)
 
 
-def update(config_file_name, docx_file_name):
+def update(config_file_name, microsoft_file_name):
     """
-    Update all the editable metadata in the given .docx file according to the given config file.
+    Update all the editable metadata in the given microsoft file according to the given config file.
 
     :param config_file_name: name of .json config file
     :type config_file_name: str
-    :param docx_file_name: name of .docx file
-    :type docx_file_name: str
+    :param microsoft_file_name: name of microsoft file
+    :type microsoft_file_name: str
     :return: None
     """
     config = read_json(config_file_name)
@@ -86,55 +86,56 @@ def update(config_file_name, docx_file_name):
         print("There isn't any chosen personal field to remove")
         return
 
-    docx_file_name = remove_format(docx_file_name)
-    unzipped_dir, source_file = extract_docx(docx_file_name)
+    microsoft_format = get_microsoft_format(microsoft_file_name)
+    unzipped_dir, source_file = extract(microsoft_file_name)
     doc_props_dir = os.path.join(unzipped_dir, "docProps")
     core_xml_path = os.path.join(doc_props_dir, "core.xml")
     app_xml_path = os.path.join(doc_props_dir, "app.xml")
 
     if has_core_tags:
         if os.path.exists(core_xml_path):
-            e_core = ET.parse(core_xml_path)
+            e_core = lxml.parse(core_xml_path)
             for xml_element in e_core.iter():
                 for personal_field in personal_fields_core_xml:
                     associated_xml_tag = CORE_XML_MAP[personal_field]
                     if (associated_xml_tag in xml_element.tag):
                         xml_element.text = config[personal_field]
-            e_core.write(core_xml_path, "utf-8", True, None, "xml")
+            e_core.write(core_xml_path)
 
     if has_app_tags:
         if os.path.exists(app_xml_path):
-            e_app = ET.parse(app_xml_path)
+            e_app = lxml.parse(app_xml_path)
             for xml_element in e_app.iter():
                 for personal_field in personal_fields_app_xml:
                     associated_xml_tag = APP_XML_MAP[personal_field]
                     if (associated_xml_tag in xml_element.tag):
                         xml_element.text = config[personal_field]
-            e_app.write(app_xml_path, "utf-8", True, None, "xml")
+            e_app.write(app_xml_path)
 
-    modified_docx = docx_file_name + "_updated"
-    with zipfile.ZipFile(modified_docx + ".docx", "w") as docx:
-        for filename in source_file.namelist():
-            docx.write(os.path.join(unzipped_dir, filename), filename)
+    modified = microsoft_file_name[:microsoft_file_name.rfind('.')] + "_updated"
+    with zipfile.ZipFile(modified + "." + microsoft_format, "w") as file:
+        for file_name in source_file.namelist():
+            file.write(os.path.join(unzipped_dir, file_name), file_name)
+        file.close()
     shutil.rmtree(unzipped_dir)
 
 
 def update_all(config_file_name):
     """
-    Update all the editable metadata in any .docx file in the current directory according to the given config file.
+    Update all the editable metadata in any microsoft file in the current directory according to the given config file.
 
     :param config_file_name: name of .json config file
     :type config_file_name: str
     :return: None
     """
     path = os.getcwd()
     dir_list = os.listdir(path)
-    docx_files = []
+    microsoft_files = []
     for item in dir_list:
-        if ".docx" in item:
-            docx_files.append(item)
-    for docx_file in docx_files:
-        update(config_file_name, docx_file)
+        if get_microsoft_format(item) is not None:
+            microsoft_files.append(item)
+    for microsoft_file in microsoft_files:
+        update(config_file_name, microsoft_file)
 
 
 def dmeta_help():

dmeta/params.py

@@ -31,3 +31,8 @@
     "company": "Company",
     "manager": "Manager"
 }
+SUPPORTED_MICROSOFT_FORMATS = [
+    "docx",
+    "pptx",
+    "xlsx"
+]

dmeta/util.py

@@ -5,6 +5,7 @@
 from shutil import rmtree
 from zipfile import ZipFile
 import defusedxml.ElementTree as ET
+from .params import SUPPORTED_MICROSOFT_FORMATS
 
 
 def extract_namespaces(xml_file_path):
@@ -18,43 +19,43 @@ def extract_namespaces(xml_file_path):
     namespaces = {}
     tree = ET.parse(xml_file_path)
     root = tree.getroot()
-
     # Extract namespaces from the root element
     for key, value in root.attrib.items():
         if key.startswith('xmlns:'):
             _, _, cropped_name = key.partition(':')
             namespaces[cropped_name] = value
         elif key == 'xmlns':
             namespaces['xmlns'] = value
-
     return namespaces
 
 
-def remove_format(docx_file_name):
+def get_microsoft_format(file_name):
     """
-    Remove the format from the end of the .docx file name.
+    Extract format from the end of the given microsoft file name.
 
-    :param docx_file_name: name of .docx file
-    :type docx_file_name: str
-    :return: str (the .docx file name without format at the end)
+    :param file_name: name of the microsoft file name
+    :type file_name: str
+    :return: str
     """
-    last_dot_index = docx_file_name.rfind('.')
-    if (last_dot_index != -1):
-        docx_file_name = docx_file_name[:last_dot_index]
-    return docx_file_name
+    last_dot_index = file_name.rfind('.')
+    if (last_dot_index == -1):
+        return None
+    format = file_name[last_dot_index + 1:]
+    if format not in SUPPORTED_MICROSOFT_FORMATS:
+        return None
+    return format
 
 
-def extract_docx(docx_file_name):
+def extract(file_name):
     """
-    Zip and extract the .docx file.
+    Zip and extract the microsoft file.
 
-    :param docx_file_name: name of .docx file
-    :type docx_file_name: str
+    :param file_name: name of microsoft file
+    :type file_name: str
     :return: (str, ZipFile) as (unzipped directory, ZipFile instance to work with the extracted content)
     """
-    docx_file_name = remove_format(docx_file_name)
-    source_file = ZipFile(docx_file_name + ".docx")
-    unzipped_dir = os.path.join(docx_file_name + "_unzipped")
+    source_file = ZipFile(file_name)
+    unzipped_dir = os.path.join(file_name[:file_name.rfind(".")] + "_unzipped")
     rmtree(unzipped_dir, ignore_errors=True)
     os.mkdir(unzipped_dir)
     source_file.extractall(unzipped_dir)

requirements.txt

@@ -1,2 +1,3 @@
 art>=1.8
-defusedxml>=0.5.0
+defusedxml>=0.7.1
+lxml>=5.2.2

tests/test_dmeta.py

@@ -1,5 +1,5 @@
 from dmeta.functions import update, update_all, clear, clear_all
-import os 
+import os
 
 TESTS_DIR_PATH = os.path.join(os.getcwd(), "tests")