feat(migrations): try to fix the migrations service
This commit is contained in:
perf3ct
parent
e1e949cf65
commit
cd35f877b1
|
|
@ -8,6 +8,7 @@ services:
|
|||
- JWT_SECRET=your-super-secret-jwt-key-change-this-in-production
|
||||
- UPLOAD_PATH=/app/uploads
|
||||
- WATCH_FOLDER=/app/watch
|
||||
- RUST_BACKTRACE=1
|
||||
volumes:
|
||||
- uploads:/app/uploads
|
||||
- watch:/app/watch
|
||||
|
|
|
|||
|
|
@ -22,6 +22,12 @@ CREATE TABLE IF NOT EXISTS documents (
|
|||
mime_type VARCHAR(100) NOT NULL,
|
||||
content TEXT,
|
||||
ocr_text TEXT,
|
||||
ocr_confidence REAL,
|
||||
ocr_word_count INT,
|
||||
ocr_processing_time_ms INT,
|
||||
ocr_status VARCHAR(20) DEFAULT 'pending',
|
||||
ocr_error TEXT,
|
||||
ocr_completed_at TIMESTAMPTZ,
|
||||
tags TEXT[] DEFAULT '{}',
|
||||
created_at TIMESTAMPTZ DEFAULT NOW(),
|
||||
updated_at TIMESTAMPTZ DEFAULT NOW(),
|
||||
|
|
@ -36,6 +42,8 @@ CREATE INDEX IF NOT EXISTS idx_documents_tags ON documents USING GIN(tags);
|
|||
CREATE INDEX IF NOT EXISTS idx_documents_content_search ON documents USING GIN(to_tsvector('english', COALESCE(content, '') || ' ' || COALESCE(ocr_text, '')));
|
||||
CREATE INDEX IF NOT EXISTS idx_documents_filename_trgm ON documents USING GIN(filename gin_trgm_ops);
|
||||
CREATE INDEX IF NOT EXISTS idx_documents_content_trgm ON documents USING GIN((COALESCE(content, '') || ' ' || COALESCE(ocr_text, '')) gin_trgm_ops);
|
||||
CREATE INDEX IF NOT EXISTS idx_documents_ocr_confidence ON documents(ocr_confidence) WHERE ocr_confidence IS NOT NULL;
|
||||
CREATE INDEX IF NOT EXISTS idx_documents_ocr_word_count ON documents(ocr_word_count) WHERE ocr_word_count IS NOT NULL;
|
||||
|
||||
-- Create settings table
|
||||
CREATE TABLE IF NOT EXISTS settings (
|
||||
|
|
@ -57,6 +65,15 @@ CREATE TABLE IF NOT EXISTS settings (
|
|||
memory_limit_mb INT DEFAULT 512,
|
||||
cpu_priority VARCHAR(10) DEFAULT 'normal',
|
||||
enable_background_ocr BOOLEAN DEFAULT TRUE,
|
||||
ocr_page_segmentation_mode INT DEFAULT 3,
|
||||
ocr_engine_mode INT DEFAULT 3,
|
||||
ocr_min_confidence REAL DEFAULT 30.0,
|
||||
ocr_dpi INT DEFAULT 300,
|
||||
ocr_enhance_contrast BOOLEAN DEFAULT true,
|
||||
ocr_remove_noise BOOLEAN DEFAULT true,
|
||||
ocr_detect_orientation BOOLEAN DEFAULT true,
|
||||
ocr_whitelist_chars TEXT,
|
||||
ocr_blacklist_chars TEXT,
|
||||
created_at TIMESTAMPTZ DEFAULT NOW(),
|
||||
updated_at TIMESTAMPTZ DEFAULT NOW()
|
||||
);
|
||||
22
src/db.rs
22
src/db.rs
|
|
@ -322,9 +322,9 @@ impl Database {
|
|||
pub async fn create_document(&self, document: Document) -> Result<Document> {
|
||||
let row = sqlx::query(
|
||||
r#"
|
||||
INSERT INTO documents (id, filename, original_filename, file_path, file_size, mime_type, content, ocr_text, tags, created_at, updated_at, user_id)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12)
|
||||
RETURNING id, filename, original_filename, file_path, file_size, mime_type, content, ocr_text, tags, created_at, updated_at, user_id
|
||||
INSERT INTO documents (id, filename, original_filename, file_path, file_size, mime_type, content, ocr_text, ocr_confidence, ocr_word_count, ocr_processing_time_ms, ocr_status, ocr_error, ocr_completed_at, tags, created_at, updated_at, user_id)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12, $13, $14, $15, $16, $17, $18)
|
||||
RETURNING id, filename, original_filename, file_path, file_size, mime_type, content, ocr_text, ocr_confidence, ocr_word_count, ocr_processing_time_ms, ocr_status, ocr_error, ocr_completed_at, tags, created_at, updated_at, user_id
|
||||
"#
|
||||
)
|
||||
.bind(document.id)
|
||||
|
|
@ -335,6 +335,12 @@ impl Database {
|
|||
.bind(&document.mime_type)
|
||||
.bind(&document.content)
|
||||
.bind(&document.ocr_text)
|
||||
.bind(document.ocr_confidence)
|
||||
.bind(document.ocr_word_count)
|
||||
.bind(document.ocr_processing_time_ms)
|
||||
.bind(&document.ocr_status)
|
||||
.bind(&document.ocr_error)
|
||||
.bind(document.ocr_completed_at)
|
||||
.bind(&document.tags)
|
||||
.bind(document.created_at)
|
||||
.bind(document.updated_at)
|
||||
|
|
@ -355,6 +361,8 @@ impl Database {
|
|||
ocr_word_count: row.get("ocr_word_count"),
|
||||
ocr_processing_time_ms: row.get("ocr_processing_time_ms"),
|
||||
ocr_status: row.get("ocr_status"),
|
||||
ocr_error: row.get("ocr_error"),
|
||||
ocr_completed_at: row.get("ocr_completed_at"),
|
||||
tags: row.get("tags"),
|
||||
created_at: row.get("created_at"),
|
||||
updated_at: row.get("updated_at"),
|
||||
|
|
@ -393,6 +401,8 @@ impl Database {
|
|||
ocr_word_count: row.get("ocr_word_count"),
|
||||
ocr_processing_time_ms: row.get("ocr_processing_time_ms"),
|
||||
ocr_status: row.get("ocr_status"),
|
||||
ocr_error: row.get("ocr_error"),
|
||||
ocr_completed_at: row.get("ocr_completed_at"),
|
||||
tags: row.get("tags"),
|
||||
created_at: row.get("created_at"),
|
||||
updated_at: row.get("updated_at"),
|
||||
|
|
@ -431,6 +441,8 @@ impl Database {
|
|||
ocr_word_count: row.get("ocr_word_count"),
|
||||
ocr_processing_time_ms: row.get("ocr_processing_time_ms"),
|
||||
ocr_status: row.get("ocr_status"),
|
||||
ocr_error: row.get("ocr_error"),
|
||||
ocr_completed_at: row.get("ocr_completed_at"),
|
||||
tags: row.get("tags"),
|
||||
created_at: row.get("created_at"),
|
||||
updated_at: row.get("updated_at"),
|
||||
|
|
@ -499,6 +511,8 @@ impl Database {
|
|||
ocr_word_count: row.get("ocr_word_count"),
|
||||
ocr_processing_time_ms: row.get("ocr_processing_time_ms"),
|
||||
ocr_status: row.get("ocr_status"),
|
||||
ocr_error: row.get("ocr_error"),
|
||||
ocr_completed_at: row.get("ocr_completed_at"),
|
||||
tags: row.get("tags"),
|
||||
created_at: row.get("created_at"),
|
||||
updated_at: row.get("updated_at"),
|
||||
|
|
@ -580,7 +594,7 @@ impl Database {
|
|||
CASE WHEN filename ILIKE '%' || "#
|
||||
));
|
||||
builder.push_bind(&search.query);
|
||||
builder.push(&format!(r#"' || '%' THEN 0.8 ELSE 0 END,
|
||||
builder.push(&format!(r#" || '%' THEN 0.8 ELSE 0 END,
|
||||
ts_rank(to_tsvector('english', COALESCE(content, '') || ' ' || COALESCE(ocr_text, '')), {}('english', "#, query_function));
|
||||
builder.push_bind(&search.query);
|
||||
builder.push(&format!(r#"))
|
||||
|
|
|
|||
|
|
@ -62,6 +62,8 @@ impl FileService {
|
|||
ocr_word_count: None,
|
||||
ocr_processing_time_ms: None,
|
||||
ocr_status: Some("pending".to_string()),
|
||||
ocr_error: None,
|
||||
ocr_completed_at: None,
|
||||
tags: Vec::new(),
|
||||
created_at: Utc::now(),
|
||||
updated_at: Utc::now(),
|
||||
|
|
|
|||
22
src/main.rs
22
src/main.rs
|
|
@ -82,6 +82,28 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
|
|||
}
|
||||
}
|
||||
|
||||
// Debug: Check what columns exist in documents table
|
||||
let columns_result = sqlx::query(
|
||||
"SELECT column_name FROM information_schema.columns
|
||||
WHERE table_name = 'documents' AND table_schema = 'public'
|
||||
ORDER BY ordinal_position"
|
||||
)
|
||||
.fetch_all(&db.pool)
|
||||
.await;
|
||||
|
||||
match columns_result {
|
||||
Ok(rows) => {
|
||||
info!("Columns in documents table:");
|
||||
for row in rows {
|
||||
let column_name: String = row.get("column_name");
|
||||
info!(" - {}", column_name);
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
error!("Failed to check columns: {}", e);
|
||||
}
|
||||
}
|
||||
|
||||
// Seed admin user
|
||||
seed::seed_admin_user(&db).await?;
|
||||
|
||||
|
|
|
|||
|
|
@ -54,6 +54,8 @@ pub struct Document {
|
|||
pub ocr_word_count: Option<i32>,
|
||||
pub ocr_processing_time_ms: Option<i32>,
|
||||
pub ocr_status: Option<String>,
|
||||
pub ocr_error: Option<String>,
|
||||
pub ocr_completed_at: Option<DateTime<Utc>>,
|
||||
pub tags: Vec<String>,
|
||||
pub created_at: DateTime<Utc>,
|
||||
pub updated_at: DateTime<Utc>,
|
||||
|
|
|
|||
Loading…
Reference in New Issue