From 279e18e781d2c4813bd7495e77a5cf0f7e28e852 Mon Sep 17 00:00:00 2001
From: Maximilian Walz <mw85859@win.edag.de>
Date: Wed, 16 Apr 2025 16:22:59 +0200
Subject: [PATCH] Add readme and first script

---
 ContextExtractor.ps1 | 132 +++++++++++++++++++++++++++++++++++++++++++
 README.md            |  12 ++++
 2 files changed, 144 insertions(+)
 create mode 100644 ContextExtractor.ps1
 create mode 100644 README.md

diff --git a/ContextExtractor.ps1 b/ContextExtractor.ps1
new file mode 100644
index 0000000..78952a5
--- /dev/null
+++ b/ContextExtractor.ps1
@@ -0,0 +1,132 @@
+param (
+    [Parameter(Mandatory=$false)]
+    [string[]]$AdditionalExtensions,
+
+    [Parameter(Mandatory=$false)]
+    [string[]]$AdditionalFiles,
+
+    [Parameter(Mandatory=$false)]
+    [switch]$KeepLineBreaks
+)
+
+# Use current directory as the root directory
+$DirectoryPath = Get-Location
+
+# Default files to include
+$defaultFiles = @(
+    "build.gradle",
+    "application.properties"
+)
+
+# Function to check if a file is in a test package
+function Is-TestFile {
+    param (
+        [string]$FilePath
+    )
+
+    # Check if the path contains \test\ folder or .test. in the path
+    return ($FilePath -match "\\test\\") -or ($FilePath -match "\.test\.")
+}
+
+# Function to extract and minify file content with header
+function Get-FileContent {
+    param (
+        [string]$FilePath
+    )
+
+    $fileName = Split-Path -Leaf $FilePath
+    $relativePath = $FilePath.Replace($DirectoryPath, "").TrimStart("\")
+
+    $content = Get-Content -Path $FilePath -Raw
+
+    # If the KeepLineBreaks switch is not set, minify the content
+    if (-not $KeepLineBreaks) {
+        # Replace newlines with spaces, but keep any comments (preserving their start)
+        $content = $content -replace "`r`n", " " -replace "`n", " "
+        # Remove redundant spaces
+        $content = $content -replace "\s+", " "
+    }
+
+    # Create a header for this file
+    $header = "FILE: $relativePath "
+
+    return $header + $content + " "
+}
+
+Write-Host "Starting code extraction from: $DirectoryPath"
+
+# Create empty output file
+$outputPath = "output.txt"
+"" | Out-File -FilePath $outputPath -Force
+
+# Get all .java files from the /src/main/ folder only
+$srcMainPath = Join-Path -Path $DirectoryPath -ChildPath "src\main"
+if (Test-Path -Path $srcMainPath) {
+    $javaFiles = Get-ChildItem -Path $srcMainPath -Recurse -Filter "*.java" |
+        Select-Object -ExpandProperty FullName
+    Write-Host "Found $($javaFiles.Count) Java files in src\main folder"
+} else {
+    $javaFiles = @()
+    Write-Warning "The src\main folder does not exist in this project"
+}
+
+# Find the default files if they exist
+$foundDefaultFiles = @()
+foreach ($file in $defaultFiles) {
+    $filePath = Get-ChildItem -Path $DirectoryPath -Recurse -Filter $file -File | Select-Object -ExpandProperty FullName
+    if ($filePath) {
+        $foundDefaultFiles += $filePath
+        Write-Host "Found default file: $file"
+    } else {
+        Write-Warning "Default file not found: $file"
+    }
+}
+
+# Find files with additional extensions if specified
+$extensionFiles = @()
+if ($AdditionalExtensions) {
+    foreach ($ext in $AdditionalExtensions) {
+        $extClean = $ext.TrimStart(".")
+        $foundFiles = Get-ChildItem -Path $DirectoryPath -Recurse -Filter "*.$extClean" |
+            Where-Object { -not (Is-TestFile -FilePath $_.FullName) } |
+            Select-Object -ExpandProperty FullName
+
+        $extensionFiles += $foundFiles
+        Write-Host "Found $($foundFiles.Count) files with extension .$extClean"
+    }
+}
+
+# Add specified additional files if they exist
+$validAdditionalFiles = @()
+if ($AdditionalFiles) {
+    foreach ($file in $AdditionalFiles) {
+        $filePath = Join-Path -Path $DirectoryPath -ChildPath $file
+        if (Test-Path -Path $filePath) {
+            $validAdditionalFiles += $filePath
+            Write-Host "Found additional file: $file"
+        } else {
+            Write-Warning "Additional file not found: $file"
+        }
+    }
+}
+
+# Combine all files
+$allFiles = $javaFiles + $foundDefaultFiles + $extensionFiles + $validAdditionalFiles | Sort-Object
+
+# Process each file
+$totalFiles = $allFiles.Count
+$processedFiles = 0
+
+foreach ($file in $allFiles) {
+    $processedFiles++
+    Write-Progress -Activity "Processing Files" -Status "Processing file $processedFiles of $totalFiles" -PercentComplete (($processedFiles / $totalFiles) * 100)
+
+    $fileContent = Get-FileContent -FilePath $file
+    Add-Content -Path $outputPath -Value $fileContent -NoNewline
+}
+
+# Add a final newline to the file
+Add-Content -Path $outputPath -Value "`n" -NoNewline
+
+$outputSize = (Get-Item -Path $outputPath).Length / 1KB
+Write-Host "Extraction complete. $processedFiles files processed and saved to $outputPath ($([Math]::Round($outputSize, 2)) KB)"
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..73d915e
--- /dev/null
+++ b/README.md
@@ -0,0 +1,12 @@
+# Content Extractor Scripts
+Scripts for generating project context for llms
+
+## ContentExtractor.ps1
+> PowerShell
+### Features:
+1. Extract all .java files
+2. Extract configured additional files
+3. Extract configured additional file types
+
+### Usage example
+> .\ContextExtractor.ps1 -AdditionalFiles "src\main\resources\static\index.html"
\ No newline at end of file