reddocx 0.0.1__tar.gz

reddocx-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Ayush Kumar
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

reddocx-0.0.1/PKG-INFO

@@ -0,0 +1,18 @@
+Metadata-Version: 2.4
+Name: reddocx
+Version: 0.0.1
+Summary: Open source implementation for track changes engine for MS Word (.docx)
+Author: Ayush Kumar
+Project-URL: Homepage, https://github.com/yourusername/reddocx
+Keywords: docx,word,track-changes,ooxml
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: lxml>=6.0.2
+Requires-Dist: lxml-stubs>=0.5.1
+Dynamic: license-file
+
+# red-docx
+Open source repository for tracking changes in Word documents.

reddocx-0.0.1/README.md

@@ -0,0 +1,2 @@
+# red-docx
+Open source repository for tracking changes in Word documents.

reddocx-0.0.1/pyproject.toml

@@ -0,0 +1,32 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "reddocx"                 
+version = "0.0.1"
+description = "Open source implementation for track changes engine for MS Word (.docx)"
+readme = "README.md"
+requires-python = ">=3.9"
+authors = [
+    { name = "Ayush Kumar" }
+]
+dependencies = [
+    "lxml>=6.0.2",
+    "lxml-stubs>=0.5.1"
+]
+
+keywords = ["docx", "word", "track-changes", "ooxml"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent"
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[project.urls]
+Homepage = "https://github.com/yourusername/reddocx"
+
+[tool.setuptools]
+package-dir = {"" = "src"}

reddocx-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

reddocx-0.0.1/src/reddocx/__init__.py

@@ -0,0 +1,3 @@
+from .core.document import DocxDocument
+
+__all__ = ["DocxDocument"]

reddocx-0.0.1/src/reddocx/core/document.py

@@ -0,0 +1,148 @@
+import zipfile
+from datetime import datetime
+from io import BytesIO
+from typing import List, Optional, Union, cast
+
+from lxml import etree
+
+from ..xml.namespace import NS
+from .package import DocxPackage
+
+
+class DocxDocument:
+    def __init__(self, source: Union[str, bytes, BytesIO]):
+        self.pkg = DocxPackage(source)
+        self.document = self.pkg.read_xml("word/document.xml")
+        self.settings = self.pkg.read_xml("word/settings.xml")
+
+    def paragraphs(self) -> List[etree._Element]:
+        return cast(
+            List[etree._Element],
+            self.document.xpath(".//w:p", namespaces=NS),
+        )
+
+    def runs(self) -> List[etree._Element]:
+        return cast(
+            List[etree._Element],
+            self.document.xpath(".//w:r", namespaces=NS),
+        )
+
+    def get_paragraph_text(
+        self,
+        paragraph: etree._Element,
+    ) -> str:
+        texts = cast(List, paragraph.xpath(".//w:t", namespaces=NS))
+        return "".join(t.text for t in texts if t.text)
+
+    def track_replace_words(
+        self, replacements: dict[str, str], author: Optional[str] = "John DOE"
+    ):
+
+        results = {}
+        revision_id = 1
+        now = datetime.utcnow().isoformat() + "Z"
+
+        paragraphs = self.paragraphs()
+
+        for idx, p in enumerate(paragraphs):
+            text = self.get_paragraph_text(p)
+
+            for old, new in replacements.items():
+                if old in text:
+
+                    results.setdefault(old, []).append(idx)
+
+                    self._apply_revision(
+                        paragraph=p,
+                        old_word=old,
+                        new_word=new,
+                        rev_id=revision_id,
+                        date=now,
+                        author=author,
+                    )
+                    revision_id += 1
+
+        return results
+
+    def _apply_revision(
+        self,
+        paragraph,
+        old_word,
+        new_word,
+        rev_id,
+        date,
+        author: Optional[str] = "John Doe",
+    ):
+        ns = NS["w"]
+
+        for run in paragraph.xpath(".//w:r", namespaces=NS):
+            texts = run.xpath(".//w:t", namespaces=NS)
+
+            for t in texts:
+                if t.text and old_word in t.text:
+
+                    parent = run.getparent()
+
+                    # delete element
+                    del_el = etree.Element(f"{{{ns}}}del")
+                    del_el.set(f"{{{ns}}}id", str(rev_id))
+                    del_el.set(f"{{{ns}}}author", str(author))
+                    del_el.set(f"{{{ns}}}date", date)
+
+                    del_run = etree.Element(f"{{{ns}}}r")
+                    del_text = etree.Element(f"{{{ns}}}delText")
+                    del_text.text = old_word
+
+                    del_run.append(del_text)
+                    del_el.append(del_run)
+
+                    # insert element
+                    ins_el = etree.Element(f"{{{ns}}}ins")
+                    ins_el.set(f"{{{ns}}}id", str(rev_id))
+                    ins_el.set(f"{{{ns}}}author", str(author))
+                    ins_el.set(f"{{{ns}}}date", date)
+
+                    ins_run = etree.Element(f"{{{ns}}}r")
+                    ins_text = etree.Element(f"{{{ns}}}t")
+                    ins_text.text = new_word
+
+                    ins_run.append(ins_text)
+                    ins_el.append(ins_run)
+
+                    parent.replace(run, del_el)
+                    parent.insert(parent.index(del_el) + 1, ins_el)
+
+                    break
+
+    def save(self) -> bytes:
+
+        buffer = BytesIO()
+
+        with zipfile.ZipFile(BytesIO(self.pkg._raw), "r") as r_file:
+            with zipfile.ZipFile(
+                buffer, "w", compression=zipfile.ZIP_DEFLATED
+            ) as o_file:
+                for item in r_file.infolist():
+                    if item.filename == "word/document.xml":
+                        o_file.writestr(
+                            item,
+                            etree.tostring(
+                                self.document,
+                                xml_declaration=True,
+                                encoding="UTF-8",
+                            ),
+                        )
+
+                    elif item.filename == "word/settings.xml":
+                        o_file.writestr(
+                            item,
+                            etree.tostring(
+                                self.settings,
+                                xml_declaration=True,
+                                encoding="UTF-8",
+                            ),
+                        )
+                    else:
+                        o_file.writestr(item, r_file.read(item.filename))
+
+        return buffer.getvalue()

reddocx-0.0.1/src/reddocx/core/package.py

@@ -0,0 +1,30 @@
+import zipfile
+from io import BytesIO
+from typing import Union
+
+from lxml import etree
+
+
+class DocxPackage:
+    def __init__(self, input_type: Union[str, bytes, BytesIO]):
+        if isinstance(input_type, str):
+            with open(input_type, "rb") as f:
+                self._raw = f.read()
+
+        elif isinstance(input_type, bytes):
+            self._raw = input_type
+
+        elif isinstance(input_type, BytesIO):
+            self._raw = input_type.getvalue()
+
+        else:
+            raise TypeError("Input Type must be path | bytes | BytesIO")
+
+        self.zip = zipfile.ZipFile(BytesIO(self._raw), "r")
+
+    def read_xml(self, part: str) -> etree._Element:
+        xml_bytes = self.zip.read(part)
+        return etree.fromstring(xml_bytes)
+
+    def list_parts(self):
+        return self.zip.namelist()

reddocx-0.0.1/src/reddocx/xml/namespace.py

@@ -0,0 +1,5 @@
+W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+NS = {
+    "w": W_NS
+}

reddocx-0.0.1/src/reddocx.egg-info/PKG-INFO

@@ -0,0 +1,18 @@
+Metadata-Version: 2.4
+Name: reddocx
+Version: 0.0.1
+Summary: Open source implementation for track changes engine for MS Word (.docx)
+Author: Ayush Kumar
+Project-URL: Homepage, https://github.com/yourusername/reddocx
+Keywords: docx,word,track-changes,ooxml
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: lxml>=6.0.2
+Requires-Dist: lxml-stubs>=0.5.1
+Dynamic: license-file
+
+# red-docx
+Open source repository for tracking changes in Word documents.

reddocx-0.0.1/src/reddocx.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+README.md
+pyproject.toml
+src/reddocx/__init__.py
+src/reddocx.egg-info/PKG-INFO
+src/reddocx.egg-info/SOURCES.txt
+src/reddocx.egg-info/dependency_links.txt
+src/reddocx.egg-info/requires.txt
+src/reddocx.egg-info/top_level.txt
+src/reddocx/core/__init__.py
+src/reddocx/core/document.py
+src/reddocx/core/package.py
+src/reddocx/xml/__init_.py
+src/reddocx/xml/namespace.py
+tests/test_loader.py

reddocx-0.0.1/src/reddocx.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

reddocx-0.0.1/src/reddocx.egg-info/requires.txt

@@ -0,0 +1,2 @@
+lxml>=6.0.2
+lxml-stubs>=0.5.1

reddocx-0.0.1/src/reddocx.egg-info/top_level.txt

@@ -0,0 +1 @@
+reddocx

reddocx-0.0.1/tests/test_loader.py

@@ -0,0 +1,12 @@
+from reddocx.core.document import DocxDocument
+
+doc = DocxDocument("sample.docx")
+
+print(doc.get_paragraph_text(doc.paragraphs()[0]))
+
+report = doc.track_replace_words({"Rippling": "hi", "team": "earth"})
+
+data = doc.save()
+output_path = "roundtrip.docx"
+with open(output_path, "wb") as f:
+    f.write(data)