Merge pull request #6 from nullable-eth/fix-tmdb-regex

feature: update regex to increase matching pattern

Author: nullable-eth

Makefile

@@ -0,0 +1,84 @@
+# Makefile for labelarr
+
+# Go parameters
+GOCMD=go
+GOBUILD=$(GOCMD) build
+GOCLEAN=$(GOCMD) clean
+GOTEST=$(GOCMD) test
+GOGET=$(GOCMD) get
+GOMOD=$(GOCMD) mod
+BINARY_NAME=labelarr
+BINARY_PATH=./cmd/labelarr
+
+# Build the application
+.PHONY: build
+build:
+	$(GOBUILD) -o $(BINARY_NAME) $(BINARY_PATH)
+
+# Run tests
+.PHONY: test
+test:
+	$(GOTEST) -v ./...
+
+# Run tests with coverage
+.PHONY: test-coverage
+test-coverage:
+	$(GOTEST) -v -cover ./...
+
+# Run tests with coverage report
+.PHONY: test-coverage-html
+test-coverage-html:
+	$(GOTEST) -v -coverprofile=coverage.out ./...
+	$(GOCMD) tool cover -html=coverage.out -o coverage.html
+	@echo "Coverage report generated: coverage.html"
+
+# Run benchmarks
+.PHONY: benchmark
+benchmark:
+	$(GOTEST) -bench=. -benchmem ./...
+
+# Clean build artifacts
+.PHONY: clean
+clean:
+	$(GOCLEAN)
+	rm -f $(BINARY_NAME)
+	rm -f coverage.out coverage.html
+
+# Download dependencies
+.PHONY: deps
+deps:
+	$(GOMOD) download
+	$(GOMOD) tidy
+
+# Run linter (requires golangci-lint to be installed)
+.PHONY: lint
+lint:
+	golangci-lint run
+
+# Run the application
+.PHONY: run
+run: build
+	./$(BINARY_NAME)
+
+# Build for multiple platforms
+.PHONY: build-all
+build-all:
+	GOOS=linux GOARCH=amd64 $(GOBUILD) -o $(BINARY_NAME)-linux-amd64 $(BINARY_PATH)
+	GOOS=windows GOARCH=amd64 $(GOBUILD) -o $(BINARY_NAME)-windows-amd64.exe $(BINARY_PATH)
+	GOOS=darwin GOARCH=amd64 $(GOBUILD) -o $(BINARY_NAME)-darwin-amd64 $(BINARY_PATH)
+
+# Help target
+.PHONY: help
+help:
+	@echo "Available targets:"
+	@echo "  build           - Build the application"
+	@echo "  test            - Run all tests"
+	@echo "  test-coverage   - Run tests with coverage"
+	@echo "  test-coverage-html - Generate HTML coverage report"
+	@echo "  benchmark       - Run benchmark tests"
+	@echo "  clean           - Clean build artifacts"
+	@echo "  deps            - Download and tidy dependencies"
+	@echo "  lint            - Run linter"
+	@echo "  run             - Build and run the application"
+	@echo "  build-all       - Build for multiple platforms"
+	@echo "  help            - Show this help message" 

README.md

@@ -150,35 +150,59 @@ services:
 The application can find TMDb IDs from multiple sources and supports flexible formats:
 
 - **Plex Metadata**: Standard TMDb agent IDs
-- **File Paths**: `{tmdb-12345}` in filenames or directory names
-- **Flexible Formats**: The TMDb ID can be detected in a variety of patterns, not just `{tmdb-12345}`. Supported patterns include:
-  - `{tmdb-12345}` (curly braces, anywhere in the folder or file name)
-  - `[tmdb-12345]` (square brackets)
-  - `(tmdb-12345)` (parentheses)
-  - `tmdb-12345` (standalone, with or without delimiters)
-  - Case-insensitive: `TMDB-12345`, `Tmdb-12345`, etc.
-  - The TMDb ID can appear in either the directory or file name, and can be surrounded by spaces or other characters.
-  - **Delimiters**: The TMDb ID pattern supports all common delimiters (such as `:`, `;`, `-`, `_`, etc.) between `tmdb` and the ID. For example:
-    - `tmdb:15448`
-    - `tmdb;15448`
-    - `tmdb-15448`
-    - `tmdb_15448`
-    - `tmdb: 15448`, `tmdb- 15448`, etc.
-    - These can appear in any of the supported bracket/brace/parenthesis formats or standalone.
-    - The pattern will **not** match `tmdb15448` (no separator).
-
-Example file paths:
+- **File Paths**: Flexible TMDb ID detection in filenames or directory names
+
+### ✅ **Supported Patterns** (Case-Insensitive)
+
+The TMDb ID detection is very flexible and supports various formats:
+
+**Direct Concatenation:**
+
+- `/movies/The Matrix (1999) tmdb603/file.mkv`
+- `/movies/Inception (2010) TMDB27205/file.mkv`
+- `/movies/Avatar (2009) Tmdb19995/file.mkv`
+
+**With Separators:**
+
+- `/movies/Interstellar (2014) tmdb:157336/file.mkv`
+- `/movies/The Dark Knight (2008) tmdb-155/file.mkv`
+- `/movies/Pulp Fiction (1994) tmdb_680/file.mkv`
+- `/movies/Fight Club (1999) tmdb=550/file.mkv`
+- `/movies/The Shawshank Redemption (1994) tmdb 278/file.mkv`
+
+**With Brackets/Braces:**
+
+- `/movies/Goodfellas (1990) {tmdb634}/file.mkv`
+- `/movies/Forrest Gump (1994) [tmdb-13]/file.mkv`
+- `/movies/The Godfather (1972) (tmdb:238)/file.mkv`
+- `/movies/Taxi Driver (1976) {tmdb=103}/file.mkv`
+- `/movies/Casablanca (1942) (tmdb 289)/file.mkv`
+
+**Mixed Examples:**
+
+- `/movies/Citizen Kane (1941) something tmdb: 15678 extra/file.mkv`
+- `/movies/Vertigo (1958) {tmdb=194884}/file.mkv`
+- `/movies/Psycho (1960) [ tmdb-539 ]/file.mkv`
+
+### ❌ **Will NOT Match**
+
+- `mytmdb12345` (preceded by alphanumeric characters)
+- `tmdb12345abc` (followed by alphanumeric characters)  
+- `tmdb` (no digits following)
+
+### 📁 **Example File Paths**
 
 ```
 /movies/The Matrix (1999) [tmdb-603]/The Matrix.mkv
 /movies/Inception (2010) (tmdb:27205)/Inception.mkv
-/movies/Avatar (2009) tmdb;19995/Avatar.mkv
+/movies/Avatar (2009) tmdb19995/Avatar.mkv
 /movies/Interstellar (2014) TMDB_157336/Interstellar.mkv
-/movies/Edge Case - {tmdb-12345}/file.mkv
+/movies/Edge Case - {tmdb=12345}/file.mkv
 /movies/Colon: [tmdb:54321]/file.mkv
 /movies/Semicolon; (tmdb;67890)/file.mkv
 /movies/Underscore_tmdb_11111/file.mkv
 /movies/ExtraSuffix tmdb-22222_extra/file.mkv
+/movies/Direct tmdb194884 format/file.mkv
 ```
 
 </details>
@@ -523,6 +547,38 @@ If you have an existing movie library without TMDb IDs in file paths:
 
 **⚠️ Note**: Large libraries may take time to rename. Consider doing this in batches during low-usage periods.
 
+### 📺 Sonarr Users: Renaming Existing Folders to Include TMDb ID
+
+If you're using Sonarr to manage your TV show collection and want to apply new folder naming that includes TMDb IDs, here's how to rename existing folders:
+
+#### **🔄 Apply the New Folder Names**
+
+To actually rename existing folders:
+
+1. **Go to the Series tab**
+
+2. **Click the Mass Editor** (three sliders icon)
+
+3. **Select the shows** you want to rename
+
+4. **At the bottom, click "Edit"**
+
+5. **In the popup:**
+   - Set the **Root Folder** to the same one it's already using (e.g., `/mnt/user/TV`)
+   - Click **"Save"**
+
+6. **Sonarr will interpret this as a move** and apply the new folder naming format without physically moving the files—just renaming the folders.
+
+#### **Example Result**
+
+After applying the new naming format, your TV show folders will include TMDb IDs:
+
+```
+/tv/Batman [tmdb-2287]/Season 3/Batman - S03E17 - The Joke's on Catwoman Bluray-1080p [tmdb-2287].mkv
+```
+
+**💡 Pro Tip**: This method works for renaming folders without actually moving files, making it safe and efficient for large TV libraries.
+
 </details>
 
 <details id="local-development">

internal/media/processor.go

@@ -498,8 +498,10 @@ func (p *Processor) extractTVShowTMDbID(item MediaItem) string {
 
 // ExtractTMDbIDFromPath extracts TMDb ID from file path using regex
 func ExtractTMDbIDFromPath(filePath string) string {
-	// Updated regex pattern to match {tmdb-123456} anywhere in the path
-	re := regexp.MustCompile(`\{tmdb-(\d+)\}`)
+	// Flexible regex pattern to match tmdb followed by digits with separators around the whole pattern
+	// Matches: tmdb123, tmdb:123, {tmdb-456}, [tmdb=789], tmdb_012, etc.
+	// Requires word boundaries or separators around the tmdb+digits pattern
+	re := regexp.MustCompile(`(?i)(?:^|[^a-zA-Z0-9])tmdb[^a-zA-Z0-9]*(\d+)(?:[^a-zA-Z0-9]|$)`)
 	matches := re.FindStringSubmatch(filePath)
 	if len(matches) > 1 {
 		return matches[1]