dirsql 0.3.5 → 0.3.7

package/README.md

@@ -17,6 +17,7 @@ Prebuilt binaries ship for linux-x64, linux-arm64, darwin-x64, darwin-arm64, and
 ## Usage
 
 ```typescript
+import { readFileSync } from "node:fs";
 import { DirSQL } from "dirsql";
 
 const db = new DirSQL({
@@ -25,7 +26,7 @@ const db = new DirSQL({
     {
       ddl: "CREATE TABLE users (name TEXT, age INTEGER)",
       glob: "data/*.json",
-      extract: (_filePath, content) => JSON.parse(content),
+      extract: (filePath) => JSON.parse(readFileSync(filePath, "utf8")),
     },
   ],
 });

package/dist/index.d.ts

@@ -4,8 +4,13 @@ export interface TableDef {
     ddl: string;
     /** Glob pattern (relative to the DirSQL root) for files backing this table. */
     glob: string;
-    /** Extract rows from a file's contents. Returns an array of row objects. */
-    extract: (filePath: string, content: string) => Record<string, unknown>[];
+    /**
+     * Produce the rows a matched file contributes. Receives the absolute
+     * filesystem path of the file. dirsql does not read file contents; if the
+     * callback needs the file body it reads the path itself (e.g.
+     * `fs.readFileSync(filePath, "utf8")`). Returns an array of row objects.
+     */
+    extract: (filePath: string) => Record<string, unknown>[];
     /** If true, reject rows with columns not declared in `ddl`. */
     strict?: boolean;
 }

package/dist/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../ts/index.ts"],"names":[],"mappings":"AAcA,iEAAiE;AACjE,MAAM,WAAW,QAAQ;IACvB,6EAA6E;IAC7E,GAAG,EAAE,MAAM,CAAC;IACZ,+EAA+E;IAC/E,IAAI,EAAE,MAAM,CAAC;IACb,4EAA4E;IAC5E,OAAO,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,KAAK,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,EAAE,CAAC;IAC1E,+DAA+D;IAC/D,MAAM,CAAC,EAAE,OAAO,CAAC;CAClB;AAED;;;;;;GAMG;AACH,MAAM,WAAW,aAAa;IAC5B,8BAA8B;IAC9B,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,8EAA8E;IAC9E,MAAM,CAAC,EAAE,QAAQ,EAAE,CAAC;IACpB,oDAAoD;IACpD,MAAM,CAAC,EAAE,MAAM,EAAE,CAAC;IAClB;;;;;;OAMG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;;;OAIG;IACH,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB;;;OAGG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAED,qDAAqD;AACrD,MAAM,WAAW,QAAQ;IACvB;;;;OAIG;IACH,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;IACrB,MAAM,EAAE,QAAQ,GAAG,QAAQ,GAAG,QAAQ,GAAG,OAAO,CAAC;IACjD,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;IACrC,MAAM,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;IACxC,KAAK,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CAC1B;AAGD,UAAU,YAAY;IACpB,KAAK,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,EAAE,CAAC,CAAC;IACvD,YAAY,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC;IAC9B,UAAU,CAAC,SAAS,EAAE,MAAM,GAAG,OAAO,CAAC,QAAQ,EAAE,CAAC,CAAC;CACpD;AAED,UAAU,uBAAuB;IAC/B,SAAS,CACP,IAAI,EAAE,MAAM,GAAG,IAAI,EACnB,MAAM,EAAE,QAAQ,EAAE,GAAG,IAAI,EACzB,MAAM,EAAE,MAAM,EAAE,GAAG,IAAI,EACvB,MAAM,EAAE,MAAM,GAAG,IAAI,EACrB,OAAO,EAAE,OAAO,GAAG,IAAI,EACvB,WAAW,EAAE,MAAM,GAAG,IAAI,GACzB,OAAO,CAAC,YAAY,CAAC,CAAC;CAC1B;AAID,UAAU,UAAU;IAClB,MAAM,EAAE,uBAAuB,CAAC;CACjC;AAaD;;;;;;;GAOG;AACH,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,UAAU,GAAG,IAAI,GAAG,IAAI,CAEjE;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AACH,qBAAa,MAAM;IACjB;;;;;;OAMG;IACH,QAAQ,CAAC,KAAK,EAAE,OAAO,CAAC,IAAI,CAAC,CAAC;IAG9B,OAAO,CAAC,MAAM,CAAgB;IAE9B,wDAAwD;gBAC5C,UAAU,EAAE,MAAM;IAC9B,yCAAyC;gBAC7B,OAAO,EAAE,aAAa;IAkBlC;;;;;;OAMG;IACG,KAAK,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,EAAE,CAAC;IAK5D;;;;;;;OAOG;IACG,YAAY,IAAI,OAAO,CAAC,IAAI,CAAC;IAKnC;;;;;;;OAOG;IACG,UAAU,CAAC,SAAS,EAAE,MAAM,GAAG,OAAO,CAAC,QAAQ,EAAE,CAAC;IAKxD;;;;;;;;;;OAUG;IACI,KAAK,IAAI,cAAc,CAAC,QAAQ,EAAE,IAAI,EAAE,OAAO,CAAC;CAaxD"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../ts/index.ts"],"names":[],"mappings":"AAcA,iEAAiE;AACjE,MAAM,WAAW,QAAQ;IACvB,6EAA6E;IAC7E,GAAG,EAAE,MAAM,CAAC;IACZ,+EAA+E;IAC/E,IAAI,EAAE,MAAM,CAAC;IACb;;;;;OAKG;IACH,OAAO,EAAE,CAAC,QAAQ,EAAE,MAAM,KAAK,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,EAAE,CAAC;IACzD,+DAA+D;IAC/D,MAAM,CAAC,EAAE,OAAO,CAAC;CAClB;AAED;;;;;;GAMG;AACH,MAAM,WAAW,aAAa;IAC5B,8BAA8B;IAC9B,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,8EAA8E;IAC9E,MAAM,CAAC,EAAE,QAAQ,EAAE,CAAC;IACpB,oDAAoD;IACpD,MAAM,CAAC,EAAE,MAAM,EAAE,CAAC;IAClB;;;;;;OAMG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;;;OAIG;IACH,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB;;;OAGG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAED,qDAAqD;AACrD,MAAM,WAAW,QAAQ;IACvB;;;;OAIG;IACH,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;IACrB,MAAM,EAAE,QAAQ,GAAG,QAAQ,GAAG,QAAQ,GAAG,OAAO,CAAC;IACjD,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;IACrC,MAAM,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;IACxC,KAAK,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IACtB,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CAC1B;AAGD,UAAU,YAAY;IACpB,KAAK,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,EAAE,CAAC,CAAC;IACvD,YAAY,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC;IAC9B,UAAU,CAAC,SAAS,EAAE,MAAM,GAAG,OAAO,CAAC,QAAQ,EAAE,CAAC,CAAC;CACpD;AAED,UAAU,uBAAuB;IAC/B,SAAS,CACP,IAAI,EAAE,MAAM,GAAG,IAAI,EACnB,MAAM,EAAE,QAAQ,EAAE,GAAG,IAAI,EACzB,MAAM,EAAE,MAAM,EAAE,GAAG,IAAI,EACvB,MAAM,EAAE,MAAM,GAAG,IAAI,EACrB,OAAO,EAAE,OAAO,GAAG,IAAI,EACvB,WAAW,EAAE,MAAM,GAAG,IAAI,GACzB,OAAO,CAAC,YAAY,CAAC,CAAC;CAC1B;AAID,UAAU,UAAU;IAClB,MAAM,EAAE,uBAAuB,CAAC;CACjC;AAaD;;;;;;;GAOG;AACH,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,UAAU,GAAG,IAAI,GAAG,IAAI,CAEjE;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AACH,qBAAa,MAAM;IACjB;;;;;;OAMG;IACH,QAAQ,CAAC,KAAK,EAAE,OAAO,CAAC,IAAI,CAAC,CAAC;IAG9B,OAAO,CAAC,MAAM,CAAgB;IAE9B,wDAAwD;gBAC5C,UAAU,EAAE,MAAM;IAC9B,yCAAyC;gBAC7B,OAAO,EAAE,aAAa;IAkBlC;;;;;;OAMG;IACG,KAAK,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,EAAE,CAAC;IAK5D;;;;;;;OAOG;IACG,YAAY,IAAI,OAAO,CAAC,IAAI,CAAC;IAKnC;;;;;;;OAOG;IACG,UAAU,CAAC,SAAS,EAAE,MAAM,GAAG,OAAO,CAAC,QAAQ,EAAE,CAAC;IAKxD;;;;;;;;;;OAUG;IACI,KAAK,IAAI,cAAc,CAAC,QAAQ,EAAE,IAAI,EAAE,OAAO,CAAC;CAaxD"}

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../ts/index.ts"],"names":[],"mappings":"AAAA,yBAAyB;AACzB,EAAE;AACF,wEAAwE;AACxE,kEAAkE;AAClE,qEAAqE;AACrE,qCAAqC;AACrC,EAAE;AACF,qEAAqE;AACrE,uEAAuE;AACvE,uEAAuE;AACvE,mEAAmE;AAEnE,OAAO,EAAE,cAAc,IAAI,qBAAqB,EAAE,MAAM,qBAAqB,CAAC;AAwF9E,yEAAyE;AACzE,sEAAsE;AACtE,IAAI,IAAI,GAAsB,IAAI,CAAC;AAEnC,SAAS,OAAO;IACd,IAAI,IAAI,KAAK,IAAI,EAAE,CAAC;QAClB,IAAI,GAAG,qBAAqB,EAAgB,CAAC;IAC/C,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,mBAAmB,CAAC,IAAuB;IACzD,IAAI,GAAG,IAAI,CAAC;AACd,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AACH,MAAM,OAAO,MAAM;IACjB;;;;;;OAMG;IACM,KAAK,CAAgB;IAE9B,gEAAgE;IACxD,MAAM,CAAgB;IAM9B,YAAY,GAA2B;QACrC,MAAM,OAAO,GACX,OAAO,GAAG,KAAK,QAAQ,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;QAClD,MAAM,IAAI,GAAG,OAAO,EAAE,CAAC,MAAM,CAAC;QAC9B,MAAM,WAAW,GAAG,IAAI,CAAC,SAAS,CAChC,OAAO,CAAC,IAAI,IAAI,IAAI,EACpB,OAAO,CAAC,MAAM,IAAI,IAAI,EACtB,OAAO,CAAC,MAAM,IAAI,IAAI,EACtB,OAAO,CAAC,MAAM,IAAI,IAAI,EACtB,OAAO,CAAC,OAAO,IAAI,IAAI,EACvB,OAAO,CAAC,WAAW,IAAI,IAAI,CAC5B,CAAC;QACF,IAAI,CAAC,KAAK,GAAG,WAAW,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE;YACtC,IAAI,CAAC,MAAM,GAAG,KAAK,CAAC;QACtB,CAAC,CAAC,CAAC;IACL,CAAC;IAED;;;;;;OAMG;IACH,KAAK,CAAC,KAAK,CAAC,GAAW;QACrB,MAAM,IAAI,CAAC,KAAK,CAAC;QACjB,OAAO,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IAChC,CAAC;IAED;;;;;;;OAOG;IACH,KAAK,CAAC,YAAY;QAChB,MAAM,IAAI,CAAC,KAAK,CAAC;QACjB,OAAO,IAAI,CAAC,MAAM,CAAC,YAAY,EAAE,CAAC;IACpC,CAAC;IAED;;;;;;;OAOG;IACH,KAAK,CAAC,UAAU,CAAC,SAAiB;QAChC,MAAM,IAAI,CAAC,KAAK,CAAC;QACjB,OAAO,IAAI,CAAC,MAAM,CAAC,UAAU,CAAC,SAAS,CAAC,CAAC;IAC3C,CAAC;IAED;;;;;;;;;;OAUG;IACH,KAAK,CAAC,CAAC,KAAK;QACV,MAAM,IAAI,CAAC,KAAK,CAAC;QACjB,MAAM,IAAI,CAAC,MAAM,CAAC,YAAY,EAAE,CAAC;QACjC,OAAO,IAAI,EAAE,CAAC;YACZ,qEAAqE;YACrE,gEAAgE;YAChE,sEAAsE;YACtE,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,MAAM,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC;YACjD,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;gBAC3B,MAAM,KAAK,CAAC;YACd,CAAC;QACH,CAAC;IACH,CAAC;CACF"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../ts/index.ts"],"names":[],"mappings":"AAAA,yBAAyB;AACzB,EAAE;AACF,wEAAwE;AACxE,kEAAkE;AAClE,qEAAqE;AACrE,qCAAqC;AACrC,EAAE;AACF,qEAAqE;AACrE,uEAAuE;AACvE,uEAAuE;AACvE,mEAAmE;AAEnE,OAAO,EAAE,cAAc,IAAI,qBAAqB,EAAE,MAAM,qBAAqB,CAAC;AA6F9E,yEAAyE;AACzE,sEAAsE;AACtE,IAAI,IAAI,GAAsB,IAAI,CAAC;AAEnC,SAAS,OAAO;IACd,IAAI,IAAI,KAAK,IAAI,EAAE,CAAC;QAClB,IAAI,GAAG,qBAAqB,EAAgB,CAAC;IAC/C,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,mBAAmB,CAAC,IAAuB;IACzD,IAAI,GAAG,IAAI,CAAC;AACd,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AACH,MAAM,OAAO,MAAM;IACjB;;;;;;OAMG;IACM,KAAK,CAAgB;IAE9B,gEAAgE;IACxD,MAAM,CAAgB;IAM9B,YAAY,GAA2B;QACrC,MAAM,OAAO,GACX,OAAO,GAAG,KAAK,QAAQ,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;QAClD,MAAM,IAAI,GAAG,OAAO,EAAE,CAAC,MAAM,CAAC;QAC9B,MAAM,WAAW,GAAG,IAAI,CAAC,SAAS,CAChC,OAAO,CAAC,IAAI,IAAI,IAAI,EACpB,OAAO,CAAC,MAAM,IAAI,IAAI,EACtB,OAAO,CAAC,MAAM,IAAI,IAAI,EACtB,OAAO,CAAC,MAAM,IAAI,IAAI,EACtB,OAAO,CAAC,OAAO,IAAI,IAAI,EACvB,OAAO,CAAC,WAAW,IAAI,IAAI,CAC5B,CAAC;QACF,IAAI,CAAC,KAAK,GAAG,WAAW,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE;YACtC,IAAI,CAAC,MAAM,GAAG,KAAK,CAAC;QACtB,CAAC,CAAC,CAAC;IACL,CAAC;IAED;;;;;;OAMG;IACH,KAAK,CAAC,KAAK,CAAC,GAAW;QACrB,MAAM,IAAI,CAAC,KAAK,CAAC;QACjB,OAAO,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IAChC,CAAC;IAED;;;;;;;OAOG;IACH,KAAK,CAAC,YAAY;QAChB,MAAM,IAAI,CAAC,KAAK,CAAC;QACjB,OAAO,IAAI,CAAC,MAAM,CAAC,YAAY,EAAE,CAAC;IACpC,CAAC;IAED;;;;;;;OAOG;IACH,KAAK,CAAC,UAAU,CAAC,SAAiB;QAChC,MAAM,IAAI,CAAC,KAAK,CAAC;QACjB,OAAO,IAAI,CAAC,MAAM,CAAC,UAAU,CAAC,SAAS,CAAC,CAAC;IAC3C,CAAC;IAED;;;;;;;;;;OAUG;IACH,KAAK,CAAC,CAAC,KAAK;QACV,MAAM,IAAI,CAAC,KAAK,CAAC;QACjB,MAAM,IAAI,CAAC,MAAM,CAAC,YAAY,EAAE,CAAC;QACjC,OAAO,IAAI,EAAE,CAAC;YACZ,qEAAqE;YACrE,gEAAgE;YAChE,sEAAsE;YACtE,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,MAAM,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC;YACjD,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;gBAC3B,MAAM,KAAK,CAAC;YACd,CAAC;QACH,CAAC;IACH,CAAC;CACF"}

package/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:**
 

package/docs/getting-started.md

@@ -31,7 +31,7 @@ cargo install dirsql --features cli
 
 :::
 
-See the [CLI guide](./guide/cli.md) for details on the command-line interface, and the [Rust library README](https://github.com/thekevinscott/dirsql/tree/main/packages/rust) for the library-vs-CLI feature split.
+See the [CLI section](./cli/) for details on the command-line interface, and the [Rust library README](https://github.com/thekevinscott/dirsql/tree/main/packages/rust) for the library-vs-CLI feature split.
 
 ## Quick start
 
@@ -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
 
@@ -182,5 +183,5 @@ The filesystem is always the source of truth. The database is rebuilt from files
 - [Querying](./guide/querying.md) -- SQL queries and return format
 - [File Watching](./guide/watching.md) -- real-time change events
 - [Async API](./guide/async.md) -- async ready(), query(), and watch()
-- [Command-Line Interface](./guide/cli.md) -- `dirsql` runs an HTTP server (`POST /query`, `GET /events` SSE)
+- [Using `dirsql` from the CLI](./cli/) -- `dirsql` runs an HTTP server (`POST /query`, `GET /events` SSE)
 - [Collaboration with CRDTs](./guide/crdt.md) -- multi-writer document merging alongside `dirsql`

package/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'))],
     }),
   ],
 });

package/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'))],
   },
 ];
 

package/docs/guide/querying.md

@@ -8,6 +8,10 @@ canonical: https://thekevinscott.github.io/dirsql/guide/querying
 
 Once a `DirSQL` instance is created, the initial directory scan is complete and you can run SQL queries against the indexed data.
 
+::: tip From the CLI
+The `dirsql` HTTP server exposes the same query interface over [`POST /query`](../cli/http-api.md#post-query). Send `{"sql": "..."}` and get back the same JSON array of row objects. See the [CLI section](../cli/) for the full server setup.
+:::
+
 ## Basic queries
 
 ::: code-group

package/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'))],
   },
 ];
 

package/docs/guide/watching.md

@@ -8,6 +8,10 @@ canonical: https://thekevinscott.github.io/dirsql/guide/watching
 
 `dirsql` can monitor the filesystem for changes and emit events when rows are inserted, updated, or deleted. This is useful for building reactive applications that respond to file changes in real time.
 
+::: tip From the CLI
+The `dirsql` HTTP server streams the same events over [`GET /events`](../cli/http-api.md#get-events) as a [Server-Sent Events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events) stream. Each `data:` payload uses the same JSON schema described in [Event types](#event-types) below. See the [CLI section](../cli/) for the full server setup.
+:::
+
 ## Starting a watch stream
 
 ::: code-group
@@ -22,7 +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())],
         ),
     ],
 )
@@ -63,7 +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())],
         ),
     ],
 )?;
@@ -88,13 +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'))],
   },
 ];
 

package/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'))],
     }),
   ],
 });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dirsql",
-  "version": "0.3.5",
+  "version": "0.3.7",
   "description": "Ephemeral SQL index over a local directory",
   "license": "MIT",
   "repository": "https://github.com/thekevinscott/dirsql",
@@ -191,15 +191,15 @@
     ]
   },
   "optionalDependencies": {
-    "@dirsql/lib-linux-x64-gnu": "0.3.5",
-    "@dirsql/lib-linux-arm64-gnu": "0.3.5",
-    "@dirsql/lib-darwin-x64": "0.3.5",
-    "@dirsql/lib-darwin-arm64": "0.3.5",
-    "@dirsql/lib-win32-x64-msvc": "0.3.5",
-    "@dirsql/cli-linux-x64-gnu": "0.3.5",
-    "@dirsql/cli-linux-arm64-gnu": "0.3.5",
-    "@dirsql/cli-darwin-x64": "0.3.5",
-    "@dirsql/cli-darwin-arm64": "0.3.5",
-    "@dirsql/cli-win32-x64-msvc": "0.3.5"
+    "@dirsql/lib-linux-x64-gnu": "0.3.7",
+    "@dirsql/lib-linux-arm64-gnu": "0.3.7",
+    "@dirsql/lib-darwin-x64": "0.3.7",
+    "@dirsql/lib-darwin-arm64": "0.3.7",
+    "@dirsql/lib-win32-x64-msvc": "0.3.7",
+    "@dirsql/cli-linux-x64-gnu": "0.3.7",
+    "@dirsql/cli-linux-arm64-gnu": "0.3.7",
+    "@dirsql/cli-darwin-x64": "0.3.7",
+    "@dirsql/cli-darwin-arm64": "0.3.7",
+    "@dirsql/cli-win32-x64-msvc": "0.3.7"
   }
 }

package/docs/guide/cli.md

@@ -1,131 +0,0 @@
----
-canonical: https://thekevinscott.github.io/dirsql/guide/cli
----
-
-# Command-Line Interface
-
-> Online: <https://thekevinscott.github.io/dirsql/guide/cli>
-
-`dirsql` starts an HTTP server that exposes identical SDK functionality.
-
-## Installation
-
-::: code-group
-
-```bash [npm]
-npx dirsql
-```
-
-```bash [PyPI]
-uvx dirsql
-```
-
-```bash [Cargo]
-# Installs the binary only (non-default feature)
-cargo install dirsql --features cli
-dirsql
-```
-
-:::
-
-::: tip For Rust library consumers
-The `cli` feature is **opt-in**. Adding `dirsql` as a library dependency (`cargo add dirsql`) pulls no CLI dependencies — only the core library. See the [Rust library README](https://github.com/thekevinscott/dirsql/tree/main/packages/rust) for details.
-:::
-
-## Subcommands
-
-| Command | Purpose |
-|---|---|
-| `dirsql` (no subcommand) | Start the long-lived HTTP server (default behavior, see below). |
-| `dirsql init` | Generate a starter `.dirsql.toml` from the contents of a directory. See [Generating a Config](./init.md). |
-
-## Running the server
-
-Run `dirsql` from the directory containing your files:
-
-```bash
-dirsql
-
-$ Running at localhost:7117
-```
-
-### Flags
-
-| Flag | Default | Description |
-|---|---|---|
-| `--config <path>` | `./.dirsql.toml` | Path to the config file. The index is rooted at the directory containing this file. |
-| `--host <addr>` | `localhost` | Bind address |
-| `--port <n>` | `7117` | TCP port to bind |
-
-## HTTP API
-
-### `POST /query`
-
-Run a SQL query. Request body is JSON:
-
-```json
-{"sql": "SELECT title, author FROM posts WHERE draft = 0"}
-```
-
-Response is a JSON array of row objects:
-
-```json
-[
-  {"title": "Hello World", "author": "alice"},
-  {"title": "Second Post", "author": "bob"}
-]
-```
-
-On error, the server returns a non-2xx status with a JSON body:
-
-```json
-{"error": "syntax error near \"SLECT\""}
-```
-
-Malformed SQL returns `400`, not `500` — the client sent bad input. Missing / unreadable config returns `503`.
-
-```bash
-curl -s http://localhost:7117/query \
-  -H 'content-type: application/json' \
-  -d '{"sql":"SELECT COUNT(*) AS n FROM posts"}' \
-  | jq
-```
-
-### `GET /events`
-
-Opens a [Server-Sent Events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events) stream of change events. Each `data:` payload is the same JSON schema the SDK emits from [`db.watch()`](./watching.md#event-types):
-
-```
-event: row
-data: {"action":"insert","table":"posts","file_path":"posts/hello.json","row":{"title":"Hello World","author":"alice"},"old_row":null}
-
-event: row
-data: {"action":"update","table":"posts","file_path":"posts/hello.json","row":{"title":"Hello, world","author":"alice"},"old_row":{"title":"Hello World","author":"alice"}}
-
-event: row
-data: {"action":"delete","table":"posts","file_path":"posts/second.json","row":{"title":"Second Post","author":"bob"},"old_row":null}
-```
-
-Errors during extraction appear as `{"action":"error",...}` events on the same stream. They do **not** terminate the stream — a malformed file is a per-event problem, not a server-wide one.
-
-```bash
-curl -N http://localhost:7117/events
-```
-
-## Piping event streams
-
-The SSE stream is easy to tee into shell tools with `curl -N` plus `jq`:
-
-```bash
-# Log every delete to a file
-curl -N http://localhost:7117/events \
-  | jq -cR 'fromjson? | select(.action=="delete")' \
-  >> deletes.log
-
-# Alert on errors
-curl -N http://localhost:7117/events \
-  | jq -c 'fromjson? | select(.action=="error")' \
-  | while read -r line; do notify-send "dirsql error" "$line"; done
-```
-
-(The `fromjson?` wrapping strips the `data:` framing; drop it if your SSE client is already parsing frames.)

package/docs/guide/config.md

@@ -1,193 +0,0 @@
----
-canonical: https://thekevinscott.github.io/dirsql/guide/config
----
-
-# Configuration File
-
-> Online: <https://thekevinscott.github.io/dirsql/guide/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`](./tables.md) whose `extract`
-function does the parsing in your host language.
-
-## Basic Example
-
-```toml
-[dirsql]
-ignore = ["node_modules/**", ".git/**"]
-
-[[table]]
-ddl  = "CREATE TABLE posts (_path TEXT, _basename TEXT, _size INTEGER, _mtime INTEGER)"
-glob = "posts/*.md"
-```
-
-Each `posts/*.md` file produces one row. The DDL declares which stat
-virtuals are surfaced as SQL columns.
-
-## Loading a Config File
-
-Pass the config file path to the `DirSQL` constructor:
-
-::: code-group
-
-```python [Python]
-from dirsql import DirSQL
-
-db = DirSQL(config="./my-project/.dirsql.toml")
-await db.ready()
-```
-
-```rust [Rust]
-use dirsql::DirSQL;
-
-let db = DirSQL::builder()
-    .config("./my-project/.dirsql.toml")
-    .build()?;
-```
-
-```typescript [TypeScript]
-import { DirSQL } from "dirsql";
-
-// String argument is interpreted as a config file path.
-const db = new DirSQL("./my-project/.dirsql.toml");
-await db.ready;
-```
-
-:::
-
-By default, the root directory scanned is the config file's parent
-directory. Override it by passing `root` explicitly (the explicit value
-wins and a warning is emitted) or by declaring `[dirsql].root` in the
-config file itself.
-
-## Root Directory
-
-By default, the config file's parent directory is the scan root. To index
-a different location, declare `[dirsql].root` (relative paths are resolved
-relative to the config file's parent):
-
-```toml
-[dirsql]
-root = "../data"
-ignore = ["node_modules/**"]
-```
-
-## Stat Virtuals
-
-Every config-defined table can expose any of these reserved columns. Add
-the ones you want to your DDL; the rest are silently dropped.
-
-| Column | Type    | Source |
-|--------|---------|--------|
-| `_path`     | TEXT    | The file's path relative to the scan root. |
-| `_basename` | TEXT    | The filename including extension. |
-| `_dir`      | TEXT    | The parent directory path (relative to root). |
-| `_ext`      | TEXT    | The file extension, lowercased, no leading dot. |
-| `_size`     | INTEGER | Size in bytes. |
-| `_mtime`    | INTEGER | Last-modified time, unix seconds. |
-| `_ctime`    | INTEGER | Created/changed time, unix seconds. |
-
-Example query:
-
-```sql
-SELECT _basename, _size
-FROM posts
-WHERE _mtime > strftime('%s', '2024-01-01')
-ORDER BY _mtime DESC;
-```
-
-## Path Captures
-
-Use `{name}` in glob patterns to extract path segments as columns. Add a
-matching column name to the DDL and the capture is auto-populated:
-
-```toml
-[[table]]
-ddl  = "CREATE TABLE comments (thread_id TEXT, _basename TEXT, _mtime INTEGER)"
-glob = "_comments/{thread_id}/*.jsonl"
-```
-
-A file at `_comments/abc123/2024-05-05.jsonl` produces a row with
-`thread_id = "abc123"`, `_basename = "2024-05-05.jsonl"`, and `_mtime` set
-to the file's modification time.
-
-## Ignore Patterns
-
-The `ignore` list skips files and directories entirely (not even scanned):
-
-```toml
-[dirsql]
-ignore = ["node_modules/**", ".git/**", "*.pyc", "__pycache__/**"]
-```
-
-The top-level `.dirsql/` directory is always excluded, whether you list it
-or not — it is a reserved namespace for `dirsql`'s own metadata (see
-[Persistence](./persistence.md)).
-
-## Persistence
-
-Set `persist = true` to keep the SQLite database on disk between runs
-instead of rebuilding from scratch on every startup:
-
-```toml
-[dirsql]
-persist = true
-# persist_path = ".dirsql/cache.db"   # optional; this is the default
-```
-
-See [Persistence](./persistence.md) for the full reconcile algorithm,
-storage layout, and limitations.
-
-## Strict Mode
-
-By default, auto-injected virtuals that aren't in the DDL are silently
-dropped, and undeclared user-extract keys are dropped. Enable strict mode
-to error when an extract emits keys not declared in the DDL:
-
-```toml
-[[table]]
-ddl  = "CREATE TABLE comments (thread_id TEXT)"
-glob = "_comments/{thread_id}/*.jsonl"
-strict = true
-```
-
-Strict mode does **not** apply to auto-injected stat virtuals — those are
-always filtered to the DDL's declared columns regardless. Strict mode
-applies only to keys produced by an extract callback (relevant for
-programmatic [tables](./tables.md)).
-
-## Full Example
-
-```toml
-[dirsql]
-ignore = ["node_modules/**", ".git/**", "dist/**"]
-
-[[table]]
-ddl  = "CREATE TABLE comments (thread_id TEXT, _basename TEXT, _mtime INTEGER)"
-glob = "_comments/{thread_id}/*.jsonl"
-
-[[table]]
-ddl  = "CREATE TABLE documents (_path TEXT, _basename TEXT, _size INTEGER)"
-glob = "**/index.md"
-
-[[table]]
-ddl  = "CREATE TABLE logs (_path TEXT, _size INTEGER, _mtime INTEGER)"
-glob = "logs/*.csv"
-```
-
-## When you need parsed content
-
-`.dirsql.toml` does not parse file contents. For columns derived from the
-*inside* of files (frontmatter keys, JSON values, CSV cells, etc.),
-register a programmatic [`Table`](./tables.md) instead, and parse the
-bytes in your host language. Glob captures and stat virtuals are still
-auto-injected into rows produced by your extract.

package/docs/guide/init.md

@@ -1,84 +0,0 @@
----
-canonical: https://thekevinscott.github.io/dirsql/guide/init
----
-
-# Generating a config with `dirsql init`
-
-> Online: <https://thekevinscott.github.io/dirsql/guide/init>
-
-`dirsql init` generates a `.dirsql.toml` by running `claude` over the target directory.
-
-The output is limited to filesystem-fact tables. For content-aware schemas, see [Defining Tables](./tables.md).
-
-## Examples
-
-### Mixed files
-
-```
-my-downloads/
-├── archive.zip
-├── invoice.pdf
-├── notes.txt
-└── photo.jpg
-```
-
-```toml
-[[table]]
-ddl  = "CREATE TABLE files (_path TEXT, _ext TEXT, _size INTEGER)"
-glob = "*"
-```
-
-### Path captures
-
-```
-photos/
-├── 2024-01/
-│   ├── beach.jpg
-│   └── sunset.jpg
-└── 2024-02/
-    ├── snow.jpg
-    └── mountain.jpg
-```
-
-```toml
-[[table]]
-ddl  = "CREATE TABLE photos (month TEXT, _basename TEXT, _mtime INTEGER)"
-glob = "{month}/*.jpg"
-```
-
-### Multiple tables
-
-```
-my-blog/
-├── posts/
-│   ├── hello-world.md
-│   └── second.md
-└── _comments/
-    └── hello-world/
-        ├── 2024-01-15.jsonl
-        └── 2024-02-03.jsonl
-```
-
-```toml
-[[table]]
-ddl  = "CREATE TABLE posts (_basename TEXT, _mtime INTEGER, _size INTEGER)"
-glob = "posts/*.md"
-
-[[table]]
-ddl  = "CREATE TABLE comments (thread_id TEXT, _basename TEXT, _mtime INTEGER)"
-glob = "_comments/{thread_id}/*.jsonl"
-```
-
-`init` will not overwrite an existing config without `--force`.
-
-## Flags
-
-| Flag | Default | Description |
-|---|---|---|
-| `--root <path>` | cwd | Directory to scan |
-| `--output <path>` | `<root>/.dirsql.toml` | Output path |
-| `--force` | off | Overwrite if the output exists |
-
-## Authentication
-
-Requires `claude` on `PATH` and signed in. There is no separate API key. If `claude` is missing, `dirsql init` raises an exception.