Add comprehensive test infrastructure with real Anki data

.gitignore

@@ -1 +1,2 @@
 thoughts/
+data/testuser/collection.anki2-wal

Makefile

@@ -37,6 +37,15 @@ init-env:  ## init-env
 test:  ## Run all tests (unit, integration, and doc tests) with debug logging
 	pushd $(pkg_src) && RUST_LOG=INFO cargo test --all-features --all-targets -- --test-threads=1  #--nocapture
 
+.PHONY: refresh-test-fixture
+refresh-test-fixture:  ## Refresh test fixture from golden dataset
+	@echo "Refreshing test fixture from golden dataset..."
+	./ankiview/tests/fixtures/copy_golden_dataset.sh
+
+.PHONY: test-verbose
+test-verbose:  ## Run tests with verbose logging
+	pushd $(pkg_src) && RUST_LOG=debug cargo test --all-features --all-targets -- --test-threads=1 --nocapture
+
 ################################################################################
 # Building, Deploying \
 BUILDING:  ## ##################################################################

ankiview/Cargo.toml

@@ -27,6 +27,9 @@ thiserror = "2.0.11"
 tracing = "0.1.41"
 tracing-subscriber = { version = "0.3.19", features = ["env-filter"] }
 
+[[bin]]
+name = "build_test_collection"
+path = "tests/fixtures/build_test_collection.rs"
 
 [profile.release]
 codegen-units = 1

ankiview/tests/fixtures/README.md

@@ -0,0 +1,64 @@
+# Test Fixtures
+
+## Golden Test Dataset
+
+**Source**: `/Users/Q187392/dev/s/private/ankiview/data/testuser/`
+**Fixture Location**: `test_collection/`
+
+**IMPORTANT**: The golden dataset in the source location is READ-ONLY. Never modify it. All tests work with copies.
+
+### Structure
+- 15 notes with real-world content
+- Basic card type (front/back)
+- 4 media files (PNG images)
+- Collection size: ~1MB
+- Media directory: ~140KB
+
+### Content Coverage
+- Data structures (DAG, Tree, DFS)
+- Algorithms and complexity
+- Data science metrics (F1, accuracy)
+- Database concepts (star schema)
+- Embeddings and ML concepts
+- Geographic reference systems
+
+### Media Files
+- `dag.png` (37KB) - Referenced by note 1695797540370
+- `star-schema.png` (16KB) - Referenced by note 1713763428669
+- `mercator.png` (24KB) - Referenced by note 1737647330399
+- `wsg-enu2.png` (58KB) - Referenced by note 1737647330399
+
+### Refreshing Fixture from Golden Dataset
+
+If the golden dataset is updated, refresh the fixture:
+
+```bash
+chmod +x ankiview/tests/fixtures/copy_golden_dataset.sh
+./ankiview/tests/fixtures/copy_golden_dataset.sh
+```
+
+### Note IDs for Testing
+
+Use these note IDs in integration tests:
+
+```rust
+pub mod test_notes {
+    // Notes with images
+    pub const DAG_NOTE: i64 = 1695797540370;
+    pub const STAR_SCHEMA: i64 = 1713763428669;
+    pub const MERCATOR: i64 = 1737647330399;
+
+    // Text-heavy notes
+    pub const TREE: i64 = 1695797540371;
+    pub const RECURSIVE_DFS: i64 = 1695797540372;
+    pub const TAIL_RECURSION: i64 = 1698125272387;
+
+    // Data science notes
+    pub const F1_SCORE: i64 = 1714489634039;
+    pub const ACCURACY: i64 = 1714489634040;
+    pub const COLBERT: i64 = 1715928977633;
+
+    // For testing errors
+    pub const NONEXISTENT: i64 = 999999999;
+}
+```

ankiview/tests/fixtures/build_test_collection.rs

@@ -0,0 +1,120 @@
+// Build script to create test collection fixture
+// Run manually: cargo run --bin build_test_collection
+//
+// This script creates a minimal Anki collection using the Anki library.
+// Due to the complexity and version-specific nature of the Anki API,
+// an alternative approach is to manually create the collection in Anki desktop
+// and copy it here. This script serves as documentation of what the collection should contain.
+
+use anki::collection::CollectionBuilder;
+use std::path::PathBuf;
+
+fn main() -> anyhow::Result<()> {
+    println!("Creating test collection...\n");
+    println!("Note: Due to Anki API complexity, this script creates an empty collection.");
+    println!("You should add notes manually using Anki desktop, then copy the collection here.\n");
+
+    let fixture_dir = PathBuf::from("tests/fixtures/test_collection");
+
+    // Remove old collection if exists
+    if fixture_dir.exists() {
+        std::fs::remove_dir_all(&fixture_dir)?;
+    }
+    std::fs::create_dir_all(&fixture_dir)?;
+
+    let collection_path = fixture_dir.join("collection.anki2");
+    let col = CollectionBuilder::new(&collection_path).build()?;
+
+    println!("Created empty collection at: {:?}", collection_path);
+
+    // Close collection
+    col.close(None)?;
+
+    // Create media directory
+    let media_dir = fixture_dir.join("collection.media");
+    std::fs::create_dir_all(&media_dir)?;
+
+    // Create test images
+    create_test_media(&media_dir)?;
+
+    println!("\n==============================================");
+    println!("MANUAL STEPS REQUIRED:");
+    println!("==============================================\n");
+    println!("1. Open Anki desktop application");
+    println!("2. Create a new profile or use existing one");
+    println!("3. Add the following 8 notes with Basic card type:\n");
+    println!("   Note 1:");
+    println!("     Front: What is Rust?");
+    println!("     Back: A systems programming language\n");
+    println!("   Note 2:");
+    println!("     Front: What is the quadratic formula?");
+    println!(r#"     Back: <pre><code class="language-tex">$x = \frac{{-b \pm \sqrt{{b^2 - 4ac}}}}{{2a}}$</code></pre>"#);
+    println!();
+    println!("   Note 3:");
+    println!("     Front: How to create a vector in Rust?");
+    println!(r#"     Back: <pre><code class="language-rust">let v: Vec<i32> = vec![1, 2, 3];</code></pre>"#);
+    println!();
+    println!("   Note 4:");
+    println!("     Front: Rust logo");
+    println!(r#"     Back: <img src="rust-logo.png" alt="Rust logo">"#);
+    println!();
+    println!("   Note 5:");
+    println!("     Front: External image test");
+    println!(r#"     Back: <img src="https://example.com/test.jpg" alt="External">"#);
+    println!();
+    println!("   Note 6:");
+    println!("     Front: HTML entities test");
+    println!("     Back: Less than: &lt; Greater than: &gt; Ampersand: &amp;");
+    println!();
+    println!("   Note 7:");
+    println!("     Front: Question with no answer");
+    println!("     Back: (leave empty)");
+    println!();
+    println!("   Note 8:");
+    println!("     Front: Tagged question");
+    println!("     Back: Tagged answer");
+    println!("     Tags: test rust programming");
+    println!();
+    println!("4. Close Anki");
+    println!("5. Copy the collection.anki2 file to:");
+    println!("   {}", collection_path.display());
+    println!("6. Copy media files from profile's collection.media/ to:");
+    println!("   {}", media_dir.display());
+    println!("7. Note the IDs of the created notes (use SQLite browser or query)");
+    println!("8. Update tests/helpers/mod.rs with the actual note IDs\n");
+    println!("==============================================\n");
+
+    Ok(())
+}
+
+fn create_test_media(media_dir: &std::path::Path) -> anyhow::Result<()> {
+    // Create a simple 1x1 PNG file (rust-logo.png)
+    // PNG signature + IHDR chunk for 1x1 red pixel
+    let rust_logo_png = [
+        0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A, // PNG signature
+        0x00, 0x00, 0x00, 0x0D, // IHDR length
+        0x49, 0x48, 0x44, 0x52, // IHDR
+        0x00, 0x00, 0x00, 0x01, // width: 1
+        0x00, 0x00, 0x00, 0x01, // height: 1
+        0x08, 0x02, 0x00, 0x00, 0x00, // bit depth, color type, compression, filter, interlace
+        0x90, 0x77, 0x53, 0xDE, // CRC
+        0x00, 0x00, 0x00, 0x0C, // IDAT length
+        0x49, 0x44, 0x41, 0x54, // IDAT
+        0x08, 0xD7, 0x63, 0xF8, 0xCF, 0xC0, 0x00, 0x00, 0x03, 0x01, 0x01, 0x00,
+        0x18, 0xDD, 0x8D, 0xB4, // CRC
+        0x00, 0x00, 0x00, 0x00, // IEND length
+        0x49, 0x45, 0x4E, 0x44, // IEND
+        0xAE, 0x42, 0x60, 0x82, // CRC
+    ];
+
+    let rust_logo_path = media_dir.join("rust-logo.png");
+    std::fs::write(&rust_logo_path, &rust_logo_png)?;
+    println!("Created test image: {:?}", rust_logo_path);
+
+    // Create another simple PNG (sample.jpg - actually a PNG despite the name)
+    let sample_path = media_dir.join("sample.jpg");
+    std::fs::write(&sample_path, &rust_logo_png)?;
+    println!("Created test image: {:?}", sample_path);
+
+    Ok(())
+}

ankiview/tests/fixtures/copy_golden_dataset.sh

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+# Copy golden test dataset to fixtures directory
+# This script should be run from the repository root
+
+set -euo pipefail
+
+GOLDEN_SOURCE="/Users/Q187392/dev/s/private/ankiview/data/testuser"
+FIXTURE_TARGET="ankiview/tests/fixtures/test_collection"
+
+echo "Copying golden dataset to test fixtures..."
+
+# Remove old fixture if exists
+if [ -d "$FIXTURE_TARGET" ]; then
+    echo "Removing existing fixture at $FIXTURE_TARGET"
+    rm -rf "$FIXTURE_TARGET"
+fi
+
+# Create fixture directory
+mkdir -p "$FIXTURE_TARGET"
+
+# Copy collection file (close any open SQLite connections first)
+echo "Copying collection.anki2..."
+cp "$GOLDEN_SOURCE/collection.anki2" "$FIXTURE_TARGET/"
+
+# Copy media directory
+echo "Copying media files..."
+cp -r "$GOLDEN_SOURCE/collection.media" "$FIXTURE_TARGET/"
+
+# Copy media database
+echo "Copying media database..."
+cp "$GOLDEN_SOURCE/collection.media.db2" "$FIXTURE_TARGET/"
+
+# Verify files were copied
+echo ""
+echo "Verification:"
+ls -lh "$FIXTURE_TARGET/collection.anki2"
+ls -lh "$FIXTURE_TARGET/collection.media.db2"
+echo ""
+echo "Media files:"
+ls -lh "$FIXTURE_TARGET/collection.media/"
+echo ""
+echo "Golden dataset copied successfully!"
+echo ""
+echo "IMPORTANT: Do not modify files in $GOLDEN_SOURCE"
+echo "Tests will work with copies of this fixture."

ankiview/tests/helpers/mod.rs

@@ -0,0 +1,102 @@
+use ankiview::infrastructure::AnkiRepository;
+use anyhow::{Context, Result};
+use std::path::{Path, PathBuf};
+use tempfile::TempDir;
+
+/// Test fixture for working with temporary Anki collections
+#[allow(dead_code)]
+pub struct TestCollection {
+    _temp_dir: TempDir,
+    pub collection_path: PathBuf,
+    pub media_dir: PathBuf,
+}
+
+impl TestCollection {
+    /// Create a new test collection by copying the fixture
+    pub fn new() -> Result<Self> {
+        let temp_dir = tempfile::tempdir()
+            .context("Failed to create temporary directory")?;
+
+        let fixture_path = Self::fixture_collection_path();
+        let collection_path = temp_dir.path().join("collection.anki2");
+
+        // Copy fixture collection to temp location
+        std::fs::copy(&fixture_path, &collection_path)
+            .context("Failed to copy test collection fixture")?;
+
+        // Copy media directory
+        let fixture_media = fixture_path.parent().unwrap().join("collection.media");
+        let media_dir = temp_dir.path().join("collection.media");
+
+        if fixture_media.exists() {
+            copy_dir_all(&fixture_media, &media_dir)
+                .context("Failed to copy media directory")?;
+        } else {
+            std::fs::create_dir_all(&media_dir)
+                .context("Failed to create media directory")?;
+        }
+
+        Ok(Self {
+            _temp_dir: temp_dir,
+            collection_path,
+            media_dir,
+        })
+    }
+
+    /// Get path to the fixture collection
+    fn fixture_collection_path() -> PathBuf {
+        PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+            .join("tests/fixtures/test_collection/collection.anki2")
+    }
+
+    /// Open repository for this test collection
+    pub fn open_repository(&self) -> Result<AnkiRepository> {
+        AnkiRepository::new(&self.collection_path)
+    }
+}
+
+/// Recursively copy directory contents
+fn copy_dir_all(src: &Path, dst: &Path) -> Result<()> {
+    std::fs::create_dir_all(dst)?;
+    for entry in std::fs::read_dir(src)? {
+        let entry = entry?;
+        let file_type = entry.file_type()?;
+        let dst_path = dst.join(entry.file_name());
+
+        if file_type.is_dir() {
+            copy_dir_all(&entry.path(), &dst_path)?;
+        } else {
+            std::fs::copy(entry.path(), &dst_path)?;
+        }
+    }
+    Ok(())
+}
+
+/// Known test note IDs from golden dataset
+#[allow(dead_code)]
+pub mod test_notes {
+    // Notes with images - good for testing media path resolution
+    pub const DAG_NOTE: i64 = 1695797540370;  // Has dag.png image
+    pub const STAR_SCHEMA: i64 = 1713763428669;  // Has star-schema.png image
+    pub const MERCATOR: i64 = 1737647330399;  // Has mercator.png and wsg-enu2.png images
+
+    // Text-heavy notes - good for testing content rendering
+    pub const TREE: i64 = 1695797540371;
+    pub const RECURSIVE_DFS: i64 = 1695797540372;
+    pub const TAIL_RECURSION: i64 = 1698125272387;
+    pub const BIG_O: i64 = 1713934919822;
+
+    // Data science notes - good for testing HTML formatting
+    pub const F1_SCORE: i64 = 1714489634039;
+    pub const ACCURACY: i64 = 1714489634040;
+    pub const COLBERT: i64 = 1715928977633;
+
+    // Additional notes
+    pub const SCHEMA_REASONING: i64 = 1726838512787;
+    pub const RRF: i64 = 1727071084388;
+    pub const AGENT: i64 = 1748163225945;
+    pub const IMBALANCED: i64 = 1748169001421;
+
+    // For testing error cases
+    pub const NONEXISTENT: i64 = 999999999;
+}