dirsql 0.3.6__tar.gz → 0.3.7__tar.gz

{dirsql-0.3.6 → dirsql-0.3.7}/Cargo.lock

@@ -499,7 +499,7 @@ dependencies = [
 
 [[package]]
 name = "dirsql-py-ext"
-version = "0.3.6"
+version = "0.3.7"
 dependencies = [
  "dirsql",
  "pyo3",

{dirsql-0.3.6 → dirsql-0.3.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dirsql
-Version: 0.3.6
+Version: 0.3.7
 Requires-Dist: pytest>=8 ; extra == 'dev'
 Requires-Dist: pytest-describe>=2 ; extra == 'dev'
 Requires-Dist: pytest-asyncio>=0.23 ; extra == 'dev'
@@ -64,13 +64,13 @@ async def main():
             Table(
                 ddl="CREATE TABLE comments (id TEXT, body TEXT, author TEXT)",
                 glob="comments/**/index.jsonl",
-                extract=lambda path, content: [
+                extract=lambda path: [
                     {
                         "id": os.path.basename(os.path.dirname(path)),
                         "body": row["body"],
                         "author": row["author"],
                     }
-                    for line in content.splitlines()
+                    for line in open(path, encoding="utf-8").read().splitlines()
                     for row in [json.loads(line)]
                 ],
             ),
@@ -94,12 +94,12 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE posts (title TEXT, author_id TEXT)",
             glob="posts/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
         Table(
             ddl="CREATE TABLE authors (id TEXT, name TEXT)",
             glob="authors/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -139,7 +139,7 @@ async def main():
             Table(
                 ddl="CREATE TABLE items (name TEXT)",
                 glob="**/*.json",
-                extract=lambda path, content: [json.loads(content)],
+                extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
             ),
         ],
     )
@@ -165,7 +165,7 @@ Defines how files map to a SQL table.
 
 - **`ddl`** (`str`): A `CREATE TABLE` statement defining the schema.
 - **`glob`** (`str`): A glob pattern matched against file paths relative to root.
-- **`extract`** (`Callable[[str, str], list[dict]]`): A function receiving `(relative_path, file_content)` and returning a list of row dicts. Each dict's keys must match the DDL column names.
+- **`extract`** (`Callable[[str], list[dict]]`): A function receiving the matched file's absolute filesystem path and returning a list of row dicts. dirsql does not read file contents; a callback that needs the file body reads it itself (e.g. `open(path, encoding="utf-8").read()`). Each dict's keys must match the DDL column names.
 
 ### `DirSQL(root=None, *, tables=None, ignore=None, config=None)`
 

{dirsql-0.3.6/packages/python → dirsql-0.3.7}/README.md

@@ -47,13 +47,13 @@ async def main():
             Table(
                 ddl="CREATE TABLE comments (id TEXT, body TEXT, author TEXT)",
                 glob="comments/**/index.jsonl",
-                extract=lambda path, content: [
+                extract=lambda path: [
                     {
                         "id": os.path.basename(os.path.dirname(path)),
                         "body": row["body"],
                         "author": row["author"],
                     }
-                    for line in content.splitlines()
+                    for line in open(path, encoding="utf-8").read().splitlines()
                     for row in [json.loads(line)]
                 ],
             ),
@@ -77,12 +77,12 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE posts (title TEXT, author_id TEXT)",
             glob="posts/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
         Table(
             ddl="CREATE TABLE authors (id TEXT, name TEXT)",
             glob="authors/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -122,7 +122,7 @@ async def main():
             Table(
                 ddl="CREATE TABLE items (name TEXT)",
                 glob="**/*.json",
-                extract=lambda path, content: [json.loads(content)],
+                extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
             ),
         ],
     )
@@ -148,7 +148,7 @@ Defines how files map to a SQL table.
 
 - **`ddl`** (`str`): A `CREATE TABLE` statement defining the schema.
 - **`glob`** (`str`): A glob pattern matched against file paths relative to root.
-- **`extract`** (`Callable[[str, str], list[dict]]`): A function receiving `(relative_path, file_content)` and returning a list of row dicts. Each dict's keys must match the DDL column names.
+- **`extract`** (`Callable[[str], list[dict]]`): A function receiving the matched file's absolute filesystem path and returning a list of row dicts. dirsql does not read file contents; a callback that needs the file body reads it itself (e.g. `open(path, encoding="utf-8").read()`). Each dict's keys must match the DDL column names.
 
 ### `DirSQL(root=None, *, tables=None, ignore=None, config=None)`
 

{dirsql-0.3.6 → dirsql-0.3.7}/docs/api/index.md

@@ -168,15 +168,15 @@ import { Table } from 'dirsql';
 ::: code-group
 
 ```python [Python]
-Table(*, ddl: str, glob: str, extract: Callable[[str, str], list[dict]])
+Table(*, ddl: str, glob: str, extract: Callable[[str], list[dict]])
 ```
 
 ```rust [Rust]
-Table::new(ddl: &str, glob: &str, extract: fn(&str, &str) -> Vec<Value>)
+Table::new(ddl: &str, glob: &str, extract: fn(&str) -> Vec<Value>)
 ```
 
 ```typescript [TypeScript]
-new Table({ ddl: string, glob: string, extract: (path: string, content: string) => Record<string, unknown>[] })
+new Table({ ddl: string, glob: string, extract: (path: string) => Record<string, unknown>[] })
 ```
 
 :::
@@ -187,7 +187,7 @@ Defines a mapping from files to SQLite table rows.
 
 - `ddl` -- A `CREATE TABLE` statement. The table name is parsed from this DDL.
 - `glob` -- A glob pattern matched against file paths relative to the root directory.
-- `extract` -- A callable `(path, content) -> list[dict]`. Receives the relative file path and file content as strings. Returns a list of dicts/maps mapping column names to values. Return an empty list to skip a file.
+- `extract` -- A callable `(path) -> list[dict]`. Receives the absolute filesystem path of the matched file. `dirsql` does not read file contents; a callback that needs the file body reads `path` itself. Returns a list of dicts/maps mapping column names to values. Return an empty list to skip a file.
 
 **Attributes:**
 

{dirsql-0.3.6/packages/python → dirsql-0.3.7}/docs/cli/config.md

@@ -6,18 +6,7 @@ canonical: https://thekevinscott.github.io/dirsql/cli/config
 
 > Online: <https://thekevinscott.github.io/dirsql/cli/config>
 
-`dirsql` can be configured with a `.dirsql.toml` file. Tables defined this
-way produce **one row per matched file**. Each row's columns come from
-filesystem facts:
-
-- **Glob path captures** — named `{placeholder}` segments in the glob.
-- **Stat virtuals** — reserved `_`-prefixed columns for path-derived and
-  stat-derived metadata.
-
-Content interpretation (parsing JSON, CSV, frontmatter, etc.) is **not**
-configured in `.dirsql.toml`. If you need columns derived from file
-contents, register a programmatic [`Table`](../guide/tables.md) whose `extract`
-function does the parsing in your host language.
+`dirsql` can be configured with an optional `.dirsql.toml` file (if omitted, server falls back to [defaults](./server.md#defaults)). `.dirsql.toml` defines how files are parsed into SQL tables.
 
 ## Basic Example
 
@@ -30,8 +19,7 @@ ddl  = "CREATE TABLE posts (_path TEXT, _basename TEXT, _size INTEGER, _mtime IN
 glob = "posts/*.md"
 ```
 
-Each `posts/*.md` file produces one row. The DDL declares which stat
-virtuals are surfaced as SQL columns.
+Each `posts/*.md` file produces one row in the `posts` table.
 
 ## Loading a Config File
 

{dirsql-0.3.6 → dirsql-0.3.7}/docs/cli/index.md

@@ -8,16 +8,18 @@ canonical: https://thekevinscott.github.io/dirsql/cli/
 
 `dirsql` ships a command-line interface that starts an HTTP server exposing
 the same indexing, querying, and watching functionality as the SDK — no host
-language required. Point it at a directory, give it a [`.dirsql.toml`](./config.md)
-config, and query your files over HTTP.
+language required. Run it in any directory to query your files over HTTP:
+with no config it serves a default `files` table, and a
+[`.dirsql.toml`](./config.md) config defines custom tables.
 
 Everything you need to run `dirsql` as a CLI lives in this section:
 
 - **[Installation](#installation)** — get the `dirsql` binary.
 - **[Running the Server](./server.md)** — subcommands and flags.
 - **[Generating a Config (`init`)](./init.md)** — scaffold a `.dirsql.toml`.
-- **[Configuration File](./config.md)** — the `.dirsql.toml` format. The CLI
-  defines tables exclusively through this file.
+- **[Configuration File](./config.md)** — the `.dirsql.toml` format. Custom
+  tables are defined exclusively through this file; without it, the server
+  runs in [zero-config mode](./server.md#zero-config-mode).
 - **[HTTP API](./http-api.md)** — the `POST /query` and `GET /events`
   endpoints, status codes, and event streaming.
 

{dirsql-0.3.6/packages/rust → dirsql-0.3.7}/docs/cli/server.md

@@ -29,6 +29,24 @@ $ Running at localhost:7117
 The server reads tables from a [`.dirsql.toml`](./config.md) config file. By
 default it looks for `./.dirsql.toml`; override the path with `--config`.
 
+## Defaults
+
+If no config file is found, `dirsql` serves a single table named `files`, with one row per file under the directory
+
+```bash
+cd ~/some/directory   # no .dirsql.toml here
+dirsql
+
+$ Running at localhost:7117
+```
+
+```bash
+curl -s localhost:7117/query -H 'content-type: application/json' \
+  -d '{"sql":"SELECT _basename, _size FROM files ORDER BY _size DESC LIMIT 5"}'
+```
+
+A `.dirsql.toml` file will override the default.
+
 ## Flags
 
 | Flag | Default | Description |

{dirsql-0.3.6/packages/python → dirsql-0.3.7}/docs/getting-started.md

@@ -63,12 +63,12 @@ async def main():
             Table(
                 ddl="CREATE TABLE posts (title TEXT, author TEXT)",
                 glob="posts/*.json",
-                extract=lambda path, content: [json.loads(content)],
+                extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
             ),
             Table(
                 ddl="CREATE TABLE authors (id TEXT, name TEXT)",
                 glob="authors/*.json",
-                extract=lambda path, content: [json.loads(content)],
+                extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
             ),
         ],
     )
@@ -120,12 +120,12 @@ let db = DirSQL::new(
         Table::new(
             "CREATE TABLE posts (title TEXT, author TEXT)",
             "posts/*.json",
-            |_path, content| vec![row_from_json(content)],
+            |path| vec![row_from_json(&std::fs::read_to_string(path).unwrap())],
         ),
         Table::new(
             "CREATE TABLE authors (id TEXT, name TEXT)",
             "authors/*.json",
-            |_path, content| vec![row_from_json(content)],
+            |path| vec![row_from_json(&std::fs::read_to_string(path).unwrap())],
         ),
     ],
 )?;
@@ -139,18 +139,19 @@ let results = db.query(
 ```
 
 ```typescript [TypeScript]
+import { readFileSync } from 'node:fs';
 import { DirSQL, type TableDef } from 'dirsql';
 
 const tables: TableDef[] = [
   {
     ddl: 'CREATE TABLE posts (title TEXT, author TEXT)',
     glob: 'posts/*.json',
-    extract: (_path, content) => [JSON.parse(content)],
+    extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
   },
   {
     ddl: 'CREATE TABLE authors (id TEXT, name TEXT)',
     glob: 'authors/*.json',
-    extract: (_path, content) => [JSON.parse(content)],
+    extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
   },
 ];
 
@@ -169,8 +170,8 @@ const results = await db.query(`
 ## What happens at startup
 
 1. `dirsql` walks the directory tree
-2. Files matching each table's glob pattern are read
-3. The `extract` function converts file content into rows
+2. Files matching each table's glob pattern are identified
+3. The `extract` function receives each matched file's absolute path and returns rows
 4. Rows are inserted into an in-memory SQLite database
 5. SQL queries run against that database
 

{dirsql-0.3.6/packages/python → dirsql-0.3.7}/docs/guide/async.md

@@ -24,7 +24,7 @@ async def main():
             Table(
                 ddl="CREATE TABLE items (name TEXT, value INTEGER)",
                 glob="data/*.json",
-                extract=lambda path, content: [json.loads(content)],
+                extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
             ),
         ],
     )
@@ -47,7 +47,7 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
             Table::new(
                 "CREATE TABLE items (name TEXT, value INTEGER)",
                 "data/*.json",
-                |_path, content| vec![serde_json::from_str(content).unwrap()],
+                |path| vec![serde_json::from_str(&std::fs::read_to_string(path).unwrap()).unwrap()],
             ),
         ],
     )?;
@@ -59,6 +59,7 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
 ```
 
 ```typescript [TypeScript]
+import { readFileSync } from 'node:fs';
 import { DirSQL, Table } from 'dirsql';
 
 const db = new DirSQL({
@@ -67,7 +68,7 @@ const db = new DirSQL({
     new Table({
       ddl: 'CREATE TABLE items (name TEXT, value INTEGER)',
       glob: 'data/*.json',
-      extract: (_path, content) => [JSON.parse(content)],
+      extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
     }),
   ],
 });

{dirsql-0.3.6/packages/rust → dirsql-0.3.7}/docs/guide/crdt.md

@@ -60,7 +60,7 @@ db = DirSQL(
             ddl="CREATE TABLE posts (id TEXT, title TEXT, body TEXT, updated INTEGER)",
             # Match the JSON view, not the raw CRDT binary.
             glob="posts/*/view.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -76,20 +76,21 @@ let db = DirSQL::new(
         Table::new(
             "CREATE TABLE posts (id TEXT, title TEXT, body TEXT, updated INTEGER)",
             "posts/*/view.json",
-            |_path, content| vec![row_from_json(content)],
+            |path| vec![row_from_json(&std::fs::read_to_string(path).unwrap())],
         ),
     ],
 )?;
 ```
 
 ```typescript [TypeScript]
+import { readFileSync } from 'node:fs';
 import { DirSQL, type TableDef } from 'dirsql';
 
 const tables: TableDef[] = [
   {
     ddl: 'CREATE TABLE posts (id TEXT, title TEXT, body TEXT, updated INTEGER)',
     glob: 'posts/*/view.json',
-    extract: (_path, content) => [JSON.parse(content)],
+    extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
   },
 ];
 

{dirsql-0.3.6/packages/rust → dirsql-0.3.7}/docs/guide/tables.md

@@ -18,7 +18,7 @@ from dirsql import Table
 table = Table(
     ddl="CREATE TABLE comments (id TEXT, body TEXT, author TEXT)",
     glob="comments/**/index.jsonl",
-    extract=lambda path, content: [
+    extract=lambda path: [
         {"id": "...", "body": "...", "author": "..."}
     ],
 )
@@ -31,7 +31,7 @@ use std::collections::HashMap;
 let table = Table::new(
     "CREATE TABLE comments (id TEXT, body TEXT, author TEXT)",
     "comments/**/index.jsonl",
-    |_path, _content| {
+    |_path| {
         let mut row: HashMap<String, Value> = HashMap::new();
         row.insert("id".into(), Value::Text("...".into()));
         row.insert("body".into(), Value::Text("...".into()));
@@ -47,7 +47,7 @@ import type { TableDef } from 'dirsql';
 const table: TableDef = {
   ddl: 'CREATE TABLE comments (id TEXT, body TEXT, author TEXT)',
   glob: 'comments/**/index.jsonl',
-  extract: (_path, content) => [
+  extract: (_path) => [
     { id: '...', body: '...', author: '...' },
   ],
 };
@@ -89,38 +89,38 @@ Glob syntax follows standard Unix globbing rules. `**` matches any number of dir
 
 ### `extract`
 
-A callable `(path: str, content: str) -> list[dict]` that converts a file into rows.
+A callable `(path: str) -> list[dict]` that converts a file into rows.
 
-- `path` is the file path relative to the root directory
-- `content` is the file content as a string
+- `path` is the **absolute filesystem path** of the matched file
 - Return a list of dicts, where each dict maps column names to values
 - Return an empty list to skip a file
 
+`dirsql` does not read file contents for you. If your extract needs the file
+body, read it inside the callback using `path`. Callbacks that derive columns
+only from the path (or that rely solely on the auto-injected filesystem-fact
+columns) never touch the file at all.
+
 ```python
 import json
 
 # Single-object JSON files: one row per file
-extract=lambda path, content: [json.loads(content)]
+def extract(path):
+    with open(path, encoding="utf-8") as f:
+        return [json.loads(f.read())]
 
 # JSONL files: one row per line
-extract=lambda path, content: [
-    json.loads(line) for line in content.splitlines()
-]
+def extract(path):
+    with open(path, encoding="utf-8") as f:
+        return [json.loads(line) for line in f]
 
-# Derive values from the file path
+# Derive a value from the file path alone -- no file read
 import os
-extract=lambda path, content: [
-    {
-        "id": os.path.basename(os.path.dirname(path)),
-        "body": json.loads(line)["body"],
-    }
-    for line in content.splitlines()
-    for _ in [json.loads(line)]
-]
+extract = lambda path: [{"id": os.path.basename(os.path.dirname(path))}]
 
 # Conditionally skip files
-def extract(path, content):
-    data = json.loads(content)
+def extract(path):
+    with open(path, encoding="utf-8") as f:
+        data = json.loads(f.read())
     if data.get("draft"):
         return []
     return [data]
@@ -142,12 +142,12 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE posts (title TEXT, author_id TEXT)",
             glob="posts/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
         Table(
             ddl="CREATE TABLE authors (id TEXT, name TEXT)",
             glob="authors/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -184,12 +184,12 @@ let db = DirSQL::new(
         Table::new(
             "CREATE TABLE posts (title TEXT, author_id TEXT)",
             "posts/*.json",
-            |_path, content| vec![row_from_json(content)],
+            |path| vec![row_from_json(&std::fs::read_to_string(path).unwrap())],
         ),
         Table::new(
             "CREATE TABLE authors (id TEXT, name TEXT)",
             "authors/*.json",
-            |_path, content| vec![row_from_json(content)],
+            |path| vec![row_from_json(&std::fs::read_to_string(path).unwrap())],
         ),
     ],
 )?;
@@ -197,17 +197,18 @@ let db = DirSQL::new(
 
 ```typescript [TypeScript]
 import { DirSQL, type TableDef } from 'dirsql';
+import { readFileSync } from 'node:fs';
 
 const tables: TableDef[] = [
   {
     ddl: 'CREATE TABLE posts (title TEXT, author_id TEXT)',
     glob: 'posts/*.json',
-    extract: (_path, content) => [JSON.parse(content)],
+    extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
   },
   {
     ddl: 'CREATE TABLE authors (id TEXT, name TEXT)',
     glob: 'authors/*.json',
-    extract: (_path, content) => [JSON.parse(content)],
+    extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
   },
 ];
 

{dirsql-0.3.6/packages/rust → dirsql-0.3.7}/docs/guide/watching.md

@@ -26,7 +26,7 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE comments (id TEXT, body TEXT, author TEXT)",
             glob="comments/**/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -67,7 +67,7 @@ let db = DirSQL::new(
         Table::new(
             "CREATE TABLE comments (id TEXT, body TEXT, author TEXT)",
             "comments/**/*.json",
-            |_path, content| vec![row_from_json(content)],
+            |path| vec![row_from_json(&std::fs::read_to_string(path).unwrap())],
         ),
     ],
 )?;
@@ -92,13 +92,14 @@ while let Some(event) = stream.next().await {
 ```
 
 ```typescript [TypeScript]
+import { readFileSync } from 'node:fs';
 import { DirSQL, type TableDef } from 'dirsql';
 
 const tables: TableDef[] = [
   {
     ddl: 'CREATE TABLE comments (id TEXT, body TEXT, author TEXT)',
     glob: 'comments/**/*.json',
-    extract: (_path, content) => [JSON.parse(content)],
+    extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
   },
 ];
 

{dirsql-0.3.6/packages/rust → dirsql-0.3.7}/docs/index.md

@@ -35,7 +35,7 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE files (name TEXT, size INTEGER, type TEXT)",
             glob="data/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -53,7 +53,7 @@ let db = DirSQL::new(
         Table::new(
             "CREATE TABLE files (name TEXT, size INTEGER, type TEXT)",
             "data/*.json",
-            |_path, content| vec![serde_json::from_str(content).unwrap()],
+            |path| vec![serde_json::from_str(&std::fs::read_to_string(path).unwrap()).unwrap()],
         ),
     ],
 )?;
@@ -62,6 +62,7 @@ let large = db.query("SELECT * FROM files WHERE size > 1000")?;
 ```
 
 ```typescript [TypeScript]
+import { readFileSync } from 'node:fs';
 import { DirSQL, Table } from 'dirsql';
 
 const db = new DirSQL({
@@ -70,7 +71,7 @@ const db = new DirSQL({
     new Table({
       ddl: 'CREATE TABLE files (name TEXT, size INTEGER, type TEXT)',
       glob: 'data/*.json',
-      extract: (_path, content) => [JSON.parse(content)],
+      extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
     }),
   ],
 });

{dirsql-0.3.6 → dirsql-0.3.7}/packages/python/Cargo.toml

@@ -4,7 +4,7 @@ name = "dirsql-py-ext"
 # pypi/maturin handler can rewrite it via `write-version` before
 # `maturin build`. `pyproject.toml` declares `dynamic = ["version"]`
 # and maturin reads this field. Mirrors `packages/rust/Cargo.toml`.
-version = "0.3.6"
+version = "0.3.7"
 edition.workspace = true
 publish = false
 readme = "README.md"

{dirsql-0.3.6 → dirsql-0.3.7/packages/python}/README.md

@@ -47,13 +47,13 @@ async def main():
             Table(
                 ddl="CREATE TABLE comments (id TEXT, body TEXT, author TEXT)",
                 glob="comments/**/index.jsonl",
-                extract=lambda path, content: [
+                extract=lambda path: [
                     {
                         "id": os.path.basename(os.path.dirname(path)),
                         "body": row["body"],
                         "author": row["author"],
                     }
-                    for line in content.splitlines()
+                    for line in open(path, encoding="utf-8").read().splitlines()
                     for row in [json.loads(line)]
                 ],
             ),
@@ -77,12 +77,12 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE posts (title TEXT, author_id TEXT)",
             glob="posts/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
         Table(
             ddl="CREATE TABLE authors (id TEXT, name TEXT)",
             glob="authors/*.json",
-            extract=lambda path, content: [json.loads(content)],
+            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -122,7 +122,7 @@ async def main():
             Table(
                 ddl="CREATE TABLE items (name TEXT)",
                 glob="**/*.json",
-                extract=lambda path, content: [json.loads(content)],
+                extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
             ),
         ],
     )
@@ -148,7 +148,7 @@ Defines how files map to a SQL table.
 
 - **`ddl`** (`str`): A `CREATE TABLE` statement defining the schema.
 - **`glob`** (`str`): A glob pattern matched against file paths relative to root.
-- **`extract`** (`Callable[[str, str], list[dict]]`): A function receiving `(relative_path, file_content)` and returning a list of row dicts. Each dict's keys must match the DDL column names.
+- **`extract`** (`Callable[[str], list[dict]]`): A function receiving the matched file's absolute filesystem path and returning a list of row dicts. dirsql does not read file contents; a callback that needs the file body reads it itself (e.g. `open(path, encoding="utf-8").read()`). Each dict's keys must match the DDL column names.
 
 ### `DirSQL(root=None, *, tables=None, ignore=None, config=None)`
 

{dirsql-0.3.6/packages/rust → dirsql-0.3.7/packages/python}/docs/api/index.md

@@ -168,15 +168,15 @@ import { Table } from 'dirsql';
 ::: code-group
 
 ```python [Python]
-Table(*, ddl: str, glob: str, extract: Callable[[str, str], list[dict]])
+Table(*, ddl: str, glob: str, extract: Callable[[str], list[dict]])
 ```
 
 ```rust [Rust]
-Table::new(ddl: &str, glob: &str, extract: fn(&str, &str) -> Vec<Value>)
+Table::new(ddl: &str, glob: &str, extract: fn(&str) -> Vec<Value>)
 ```
 
 ```typescript [TypeScript]
-new Table({ ddl: string, glob: string, extract: (path: string, content: string) => Record<string, unknown>[] })
+new Table({ ddl: string, glob: string, extract: (path: string) => Record<string, unknown>[] })
 ```
 
 :::
@@ -187,7 +187,7 @@ Defines a mapping from files to SQLite table rows.
 
 - `ddl` -- A `CREATE TABLE` statement. The table name is parsed from this DDL.
 - `glob` -- A glob pattern matched against file paths relative to the root directory.
-- `extract` -- A callable `(path, content) -> list[dict]`. Receives the relative file path and file content as strings. Returns a list of dicts/maps mapping column names to values. Return an empty list to skip a file.
+- `extract` -- A callable `(path) -> list[dict]`. Receives the absolute filesystem path of the matched file. `dirsql` does not read file contents; a callback that needs the file body reads `path` itself. Returns a list of dicts/maps mapping column names to values. Return an empty list to skip a file.
 
 **Attributes:**