Initial version

.gitignore

@@ -0,0 +1 @@
+/target

.vscode/launch.json

@@ -0,0 +1,45 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "Debug executable 'doc-parser'",
+            "cargo": {
+                "args": [
+                    "build",
+                    "--bin=doc-parser",
+                    "--package=doc-parser"
+                ],
+                "filter": {
+                    "name": "doc-parser",
+                    "kind": "bin"
+                }
+            },
+            "args": [],
+            "cwd": "${workspaceFolder}"
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "Debug unit tests in executable 'doc-parser'",
+            "cargo": {
+                "args": [
+                    "test",
+                    "--no-run",
+                    "--bin=doc-parser",
+                    "--package=doc-parser"
+                ],
+                "filter": {
+                    "name": "doc-parser",
+                    "kind": "bin"
+                }
+            },
+            "args": [],
+            "cwd": "${workspaceFolder}"
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,9 @@
+{
+    "spellright.language": [
+        "nl"
+    ],
+    "spellright.documentTypes": [
+        "latex",
+        "plaintext"
+    ]
+}

Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "doc-parser"
+version = "0.1.0"
+edition = "2021"
+
+[dependencies]
+docx-rust = "0.1.7"
+# docx-rust = { git="https://github.com/erikvullings/docx-rs.git" }
+
+
+

convert_to_markdown.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+# Specify the input folder containing the .docx files
+input_folder="./test"
+
+# Specify the media folder where media files will be extracted
+media_folder="${input_folder}"
+
+# Loop through all .docx files in the input folder
+for file in "$input_folder"/*.docx; do
+    # Check if the file is a regular file
+    if [ -f "$file" ]; then
+        # Extract the file name without extension
+        filename=$(basename -- "$file")
+        filename_no_ext="${filename%.*}"
+
+        # Convert the .docx file to Markdown using Pandoc. See also https://stackoverflow.com/a/74654058/319711 for heading style
+        pandoc -s "$file" --wrap=none --reference-links --atx-headers --extract-media="$input_folder" -t markdown -o "${input_folder}/${filename_no_ext}.md"
+
+        echo "Converted $file to Markdown."
+    fi
+done
+