dirsql 0.3.97__tar.gz → 0.3.99__tar.gz

{dirsql-0.3.97 → dirsql-0.3.99}/Cargo.lock

@@ -500,7 +500,7 @@ dependencies = [
 
 [[package]]
 name = "dirsql-py-ext"
-version = "0.3.97"
+version = "0.3.99"
 dependencies = [
  "dirsql",
  "pyo3",

{dirsql-0.3.97 → dirsql-0.3.99}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dirsql
-Version: 0.3.97
+Version: 0.3.99
 Summary: Ephemeral SQL index over a local directory
 Keywords: sql,filesystem,directory,sqlite,index
 Author: Kevin Scott

{dirsql-0.3.97 → dirsql-0.3.99}/dirsql/_dirsql.pyi

@@ -39,7 +39,7 @@ class Table:
         *,
         ddl: str,
         glob: str,
-        extract: Callable[[str], list[Row]],
+        on_file: Callable[[str], list[Row]],
         strict: bool = False,
     ) -> None: ...
 

{dirsql-0.3.97 → dirsql-0.3.99}/docs/howto/embed.md

@@ -33,7 +33,7 @@ comments/t1/c2.json    # {"body": "nice post", "author": "bob"}
 comments/t2/c1.json    # {"body": "following up", "author": "alice"}
 ```
 
-Unlike a config-file table, a programmatic table takes an `extract`
+Unlike a config-file table, a programmatic table takes an `on_file`
 callback — your code reads each matched file and returns its rows, with
 [glob captures and stat columns](../reference/columns.md) merged on
 automatically (here, `{thread}` from the path):
@@ -47,7 +47,7 @@ import json
 from dirsql import DirSQL, Table
 
 
-def extract(path: str) -> list[dict]:
+def on_file(path: str) -> list[dict]:
     with open(path, encoding="utf-8") as f:
         return [json.load(f)]
 
@@ -59,7 +59,7 @@ async def main() -> None:
             Table(
                 ddl="CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
                 glob="comments/{thread}/*.json",
-                extract=extract,
+                on_file=on_file,
             )
         ],
     )
@@ -81,7 +81,7 @@ const db = new DirSQL({
     {
       ddl: "CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
       glob: "comments/{thread}/*.json",
-      extract: (path) => [JSON.parse(readFileSync(path, "utf8"))],
+      onFile: (path) => [JSON.parse(readFileSync(path, "utf8"))],
     },
   ],
 });
@@ -99,7 +99,7 @@ use std::collections::HashMap;
 
 use dirsql::{DirSQL, Table, Value};
 
-fn extract(path: &str) -> Vec<HashMap<String, Value>> {
+fn on_file(path: &str) -> Vec<HashMap<String, Value>> {
     let raw = std::fs::read_to_string(path).unwrap_or_default();
     let Ok(serde_json::Value::Object(obj)) = serde_json::from_str(&raw) else {
         return vec![];
@@ -119,7 +119,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
         .table(Table::new(
             "CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
             "comments/{thread}/*.json",
-            extract,
+            on_file,
         ))
         .build()?;
 

{dirsql-0.3.97/packages/python → dirsql-0.3.99}/docs/howto/extract-from-contents.md

@@ -79,6 +79,6 @@ SQLite value mapping is under
   file. If it is expensive, [keep the index across restarts](./persist.md).
 - The flagship use of `on-file` — computing embeddings — is
   [Search documents by meaning](./search-by-meaning.md).
-- Embedding `dirsql` in a program instead? The SDK's `extract` callback
+- Embedding `dirsql` in a program instead? The SDK's `on_file` callback
   fills the same role in-process — see
   [Embed `dirsql` in your application](./embed.md).

{dirsql-0.3.97/packages/rust → dirsql-0.3.99}/docs/index.md

@@ -20,7 +20,7 @@ But querying across many files is slow.
 
 ## Solution
 
-`dirsql` bridges this gap. The filesystem remains the source of truth, but you get SQL queries and real-time change events for free. Define tables with glob patterns and extract functions, and `dirsql` handles the rest.
+`dirsql` bridges this gap. The filesystem remains the source of truth, but you get SQL queries and real-time change events for free. Define tables with glob patterns and on-file callbacks, and `dirsql` handles the rest.
 
 ::: code-group
 
@@ -34,7 +34,7 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE files (name TEXT, size INTEGER, type TEXT)",
             glob="data/*.json",
-            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
+            on_file=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -70,7 +70,7 @@ const db = new DirSQL({
     new Table({
       ddl: 'CREATE TABLE files (name TEXT, size INTEGER, type TEXT)',
       glob: 'data/*.json',
-      extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
+      onFile: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
     }),
   ],
 });

{dirsql-0.3.97/packages/rust → dirsql-0.3.99}/docs/reference/columns.md

@@ -18,7 +18,7 @@ Declaring them requires nothing else. The names below aren't a protected or
 enforced namespace — nothing stops you from declaring a column with one of
 these names for an unrelated purpose, in which case dirsql's computed value
 lands there like any other fact (unless your own row source — an `on-file`
-command or SDK `extract` callback — supplies its own value for that name;
+command or SDK `on_file` callback — supplies its own value for that name;
 see [Precedence](#precedence)).
 
 ## Stat columns
@@ -71,8 +71,8 @@ A file at `_comments/abc123/2024-05-05.jsonl` produces a row with
 ## Precedence
 
 Values produced by a table's own row source — an `on-file` command's JSON
-output or an SDK `extract` callback's return value — **win** over
-auto-injected facts of the same name. An extract that explicitly emits
+output or an SDK `on_file` callback's return value — **win** over
+auto-injected facts of the same name. An `on_file` callback that explicitly emits
 `path` is honored.
 
 Injection order per row: stat columns first, then glob captures, then

{dirsql-0.3.97 → dirsql-0.3.99}/docs/reference/config.md

@@ -98,13 +98,13 @@ per-file command.
 |---|---|---|
 | `ddl` | yes | A SQLite `CREATE TABLE` statement. The table name is parsed from it. Only columns declared here are populated; auto-injected facts not in the DDL are dropped. |
 | `glob` | yes | Glob pattern matched against root-relative paths. May contain `{name}` [capture segments](./columns.md#glob-captures). Every table whose glob matches a file receives that file's rows — a file can populate multiple tables. |
-| `strict` | no (default `false`) | When `true`, rows whose keys do not exactly match the declared columns are rejected with an error: extra keys error, and every declared column must be supplied (by the command/extract output, a glob capture, or a stat column). When `false`, extra keys are dropped and missing columns become `NULL`. |
+| `strict` | no (default `false`) | When `true`, rows whose keys do not exactly match the declared columns are rejected with an error: extra keys error, and every declared column must be supplied (by the command/on-file output, a glob capture, or a stat column). When `false`, extra keys are dropped and missing columns become `NULL`. |
 | `on-file` | no | A command run once per matched file; its stdout (a JSON array of row objects) becomes the file's rows. Must be non-empty. See [Command hooks](./hooks.md#on-file). |
 
 Without `on-file`, a table produces exactly one row per matched file, built
 entirely from filesystem facts. Content interpretation (frontmatter, JSON
 fields, CSV parsing) is out of scope for plain config tables — use
-`on-file`, or a programmatic [SDK table](./sdk.md#table) with an `extract`
+`on-file`, or a programmatic [SDK table](./sdk.md#table) with an `on_file`
 callback.
 
 ```toml

{dirsql-0.3.97/packages/rust → dirsql-0.3.99}/docs/reference/sdk.md

@@ -80,7 +80,8 @@ DirSQL::builder()
     .root(root)                     // optional
     .tables(tables)                 // optional; append one with .table(t)
     .ignore(patterns)               // optional
-    .config(config_toml_path)       // optional
+    .config(config_toml_path)       // optional; repeatable — call again to
+                                    //   merge another config in call order
     .persist(cache_path)            // optional; Some(path), or None for the
                                     //   default <root>/.dirsql/cache.db
     .extensions(extensions)         // optional; append one with .extension(e)
@@ -107,7 +108,12 @@ never sets the root.
   entries are appended after any programmatic `tables`; its `ignore`
   patterns and `[[dirsql.extension]]` entries are appended likewise. The
   config file does **not** set the index root: with no explicit `root`, the
-  index roots at the process cwd.
+  index roots at the process cwd. In **Rust**, the builder's `.config()` is
+  **repeatable** — call it once per file and the configs merge in call order
+  (`[[table]]` / `ignore` / `[[dirsql.extension]]` accumulate; a duplicate
+  table name across configs errors), mirroring the CLI's repeatable
+  [`-c/--config`](./cli.md#flags). Python and TypeScript currently accept a
+  single `config` path.
 - `persist` — Keep the SQLite index on disk between runs (default off:
   ephemeral, rebuilt every startup). The cache lives at
   `<root>/.dirsql/cache.db` by default; on restart, only files whose stat
@@ -296,19 +302,19 @@ rather than waiting — an intentional, language-idiomatic difference.
 ::: code-group
 
 ```python [Python]
-Table(*, ddl: str, glob: str, extract: Callable[[str], list[dict]], strict: bool = False)
+Table(*, ddl: str, glob: str, on_file: Callable[[str], list[dict]], strict: bool = False)
 ```
 
 ```typescript [TypeScript]
-new Table({ ddl, glob, extract, strict? })
+new Table({ ddl, glob, onFile, strict? })
 // or a plain object — TableDef and Table are interchangeable:
-{ ddl: string, glob: string, extract: (path: string) => Record<string, unknown>[], strict?: boolean }
+{ ddl: string, glob: string, onFile: (path: string) => Record<string, unknown>[], strict?: boolean }
 ```
 
 ```rust [Rust]
-Table::new(ddl, glob, extract)      // extract: Fn(&str) -> Vec<Row>, infallible
-Table::try_new(ddl, glob, extract)  // extract: Fn(&str) -> Result<Vec<Row>, _>
-Table::strict(ddl, glob, extract)   // Table::new with strict = true
+Table::new(ddl, glob, on_file)      // on_file: Fn(&str) -> Vec<Row>, infallible
+Table::try_new(ddl, glob, on_file)  // on_file: Fn(&str) -> Result<Vec<Row>, _>
+Table::strict(ddl, glob, on_file)   // Table::new with strict = true
 ```
 
 :::
@@ -321,7 +327,7 @@ Maps files to table rows.
   `{name}` [captures](./columns.md#glob-captures). Every table whose glob
   matches a file receives that file's rows — a file can populate multiple
   tables.
-- `extract` — Callback receiving the matched file's full path (the root
+- `on_file` (`on_file` / `onFile`) — Callback receiving the matched file's full path (the root
   joined with the file's relative path — absolute when `root` is absolute)
   and returning the rows that file contributes. `dirsql` never reads file
   contents itself; a callback that needs the body reads the path. Return
@@ -356,7 +362,7 @@ relative to the root. Errors never terminate the stream.
 
 ## Value types
 
-An `extract` callback (and the SQLite columns it feeds) accepts:
+An `on_file` callback (and the SQLite columns it feeds) accepts:
 
 | SQLite column | Python value | TypeScript value | Rust `Value` |
 |---|---|---|---|

{dirsql-0.3.97 → dirsql-0.3.99}/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 = "0.3.97"
+version = "0.3.99"
 # abi3 note: the `abi3-py311` pyo3 feature (below) builds ONE stable-ABI
 # `cp311-abi3` wheel per platform that loads on every CPython >= 3.11
 # (matching `pyproject.toml`'s `requires-python = ">=3.11"`), instead of

{dirsql-0.3.97 → dirsql-0.3.99}/packages/python/docs/howto/embed.md

@@ -33,7 +33,7 @@ comments/t1/c2.json    # {"body": "nice post", "author": "bob"}
 comments/t2/c1.json    # {"body": "following up", "author": "alice"}
 ```
 
-Unlike a config-file table, a programmatic table takes an `extract`
+Unlike a config-file table, a programmatic table takes an `on_file`
 callback — your code reads each matched file and returns its rows, with
 [glob captures and stat columns](../reference/columns.md) merged on
 automatically (here, `{thread}` from the path):
@@ -47,7 +47,7 @@ import json
 from dirsql import DirSQL, Table
 
 
-def extract(path: str) -> list[dict]:
+def on_file(path: str) -> list[dict]:
     with open(path, encoding="utf-8") as f:
         return [json.load(f)]
 
@@ -59,7 +59,7 @@ async def main() -> None:
             Table(
                 ddl="CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
                 glob="comments/{thread}/*.json",
-                extract=extract,
+                on_file=on_file,
             )
         ],
     )
@@ -81,7 +81,7 @@ const db = new DirSQL({
     {
       ddl: "CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
       glob: "comments/{thread}/*.json",
-      extract: (path) => [JSON.parse(readFileSync(path, "utf8"))],
+      onFile: (path) => [JSON.parse(readFileSync(path, "utf8"))],
     },
   ],
 });
@@ -99,7 +99,7 @@ use std::collections::HashMap;
 
 use dirsql::{DirSQL, Table, Value};
 
-fn extract(path: &str) -> Vec<HashMap<String, Value>> {
+fn on_file(path: &str) -> Vec<HashMap<String, Value>> {
     let raw = std::fs::read_to_string(path).unwrap_or_default();
     let Ok(serde_json::Value::Object(obj)) = serde_json::from_str(&raw) else {
         return vec![];
@@ -119,7 +119,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
         .table(Table::new(
             "CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
             "comments/{thread}/*.json",
-            extract,
+            on_file,
         ))
         .build()?;
 

{dirsql-0.3.97/packages/rust → dirsql-0.3.99/packages/python}/docs/howto/extract-from-contents.md

@@ -79,6 +79,6 @@ SQLite value mapping is under
   file. If it is expensive, [keep the index across restarts](./persist.md).
 - The flagship use of `on-file` — computing embeddings — is
   [Search documents by meaning](./search-by-meaning.md).
-- Embedding `dirsql` in a program instead? The SDK's `extract` callback
+- Embedding `dirsql` in a program instead? The SDK's `on_file` callback
   fills the same role in-process — see
   [Embed `dirsql` in your application](./embed.md).

{dirsql-0.3.97 → dirsql-0.3.99}/packages/python/docs/index.md

@@ -20,7 +20,7 @@ But querying across many files is slow.
 
 ## Solution
 
-`dirsql` bridges this gap. The filesystem remains the source of truth, but you get SQL queries and real-time change events for free. Define tables with glob patterns and extract functions, and `dirsql` handles the rest.
+`dirsql` bridges this gap. The filesystem remains the source of truth, but you get SQL queries and real-time change events for free. Define tables with glob patterns and on-file callbacks, and `dirsql` handles the rest.
 
 ::: code-group
 
@@ -34,7 +34,7 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE files (name TEXT, size INTEGER, type TEXT)",
             glob="data/*.json",
-            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
+            on_file=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -70,7 +70,7 @@ const db = new DirSQL({
     new Table({
       ddl: 'CREATE TABLE files (name TEXT, size INTEGER, type TEXT)',
       glob: 'data/*.json',
-      extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
+      onFile: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
     }),
   ],
 });

{dirsql-0.3.97 → dirsql-0.3.99}/packages/python/docs/reference/columns.md

@@ -18,7 +18,7 @@ Declaring them requires nothing else. The names below aren't a protected or
 enforced namespace — nothing stops you from declaring a column with one of
 these names for an unrelated purpose, in which case dirsql's computed value
 lands there like any other fact (unless your own row source — an `on-file`
-command or SDK `extract` callback — supplies its own value for that name;
+command or SDK `on_file` callback — supplies its own value for that name;
 see [Precedence](#precedence)).
 
 ## Stat columns
@@ -71,8 +71,8 @@ A file at `_comments/abc123/2024-05-05.jsonl` produces a row with
 ## Precedence
 
 Values produced by a table's own row source — an `on-file` command's JSON
-output or an SDK `extract` callback's return value — **win** over
-auto-injected facts of the same name. An extract that explicitly emits
+output or an SDK `on_file` callback's return value — **win** over
+auto-injected facts of the same name. An `on_file` callback that explicitly emits
 `path` is honored.
 
 Injection order per row: stat columns first, then glob captures, then

{dirsql-0.3.97/packages/rust → dirsql-0.3.99/packages/python}/docs/reference/config.md

@@ -98,13 +98,13 @@ per-file command.
 |---|---|---|
 | `ddl` | yes | A SQLite `CREATE TABLE` statement. The table name is parsed from it. Only columns declared here are populated; auto-injected facts not in the DDL are dropped. |
 | `glob` | yes | Glob pattern matched against root-relative paths. May contain `{name}` [capture segments](./columns.md#glob-captures). Every table whose glob matches a file receives that file's rows — a file can populate multiple tables. |
-| `strict` | no (default `false`) | When `true`, rows whose keys do not exactly match the declared columns are rejected with an error: extra keys error, and every declared column must be supplied (by the command/extract output, a glob capture, or a stat column). When `false`, extra keys are dropped and missing columns become `NULL`. |
+| `strict` | no (default `false`) | When `true`, rows whose keys do not exactly match the declared columns are rejected with an error: extra keys error, and every declared column must be supplied (by the command/on-file output, a glob capture, or a stat column). When `false`, extra keys are dropped and missing columns become `NULL`. |
 | `on-file` | no | A command run once per matched file; its stdout (a JSON array of row objects) becomes the file's rows. Must be non-empty. See [Command hooks](./hooks.md#on-file). |
 
 Without `on-file`, a table produces exactly one row per matched file, built
 entirely from filesystem facts. Content interpretation (frontmatter, JSON
 fields, CSV parsing) is out of scope for plain config tables — use
-`on-file`, or a programmatic [SDK table](./sdk.md#table) with an `extract`
+`on-file`, or a programmatic [SDK table](./sdk.md#table) with an `on_file`
 callback.
 
 ```toml

{dirsql-0.3.97 → dirsql-0.3.99/packages/python}/docs/reference/sdk.md

@@ -80,7 +80,8 @@ DirSQL::builder()
     .root(root)                     // optional
     .tables(tables)                 // optional; append one with .table(t)
     .ignore(patterns)               // optional
-    .config(config_toml_path)       // optional
+    .config(config_toml_path)       // optional; repeatable — call again to
+                                    //   merge another config in call order
     .persist(cache_path)            // optional; Some(path), or None for the
                                     //   default <root>/.dirsql/cache.db
     .extensions(extensions)         // optional; append one with .extension(e)
@@ -107,7 +108,12 @@ never sets the root.
   entries are appended after any programmatic `tables`; its `ignore`
   patterns and `[[dirsql.extension]]` entries are appended likewise. The
   config file does **not** set the index root: with no explicit `root`, the
-  index roots at the process cwd.
+  index roots at the process cwd. In **Rust**, the builder's `.config()` is
+  **repeatable** — call it once per file and the configs merge in call order
+  (`[[table]]` / `ignore` / `[[dirsql.extension]]` accumulate; a duplicate
+  table name across configs errors), mirroring the CLI's repeatable
+  [`-c/--config`](./cli.md#flags). Python and TypeScript currently accept a
+  single `config` path.
 - `persist` — Keep the SQLite index on disk between runs (default off:
   ephemeral, rebuilt every startup). The cache lives at
   `<root>/.dirsql/cache.db` by default; on restart, only files whose stat
@@ -296,19 +302,19 @@ rather than waiting — an intentional, language-idiomatic difference.
 ::: code-group
 
 ```python [Python]
-Table(*, ddl: str, glob: str, extract: Callable[[str], list[dict]], strict: bool = False)
+Table(*, ddl: str, glob: str, on_file: Callable[[str], list[dict]], strict: bool = False)
 ```
 
 ```typescript [TypeScript]
-new Table({ ddl, glob, extract, strict? })
+new Table({ ddl, glob, onFile, strict? })
 // or a plain object — TableDef and Table are interchangeable:
-{ ddl: string, glob: string, extract: (path: string) => Record<string, unknown>[], strict?: boolean }
+{ ddl: string, glob: string, onFile: (path: string) => Record<string, unknown>[], strict?: boolean }
 ```
 
 ```rust [Rust]
-Table::new(ddl, glob, extract)      // extract: Fn(&str) -> Vec<Row>, infallible
-Table::try_new(ddl, glob, extract)  // extract: Fn(&str) -> Result<Vec<Row>, _>
-Table::strict(ddl, glob, extract)   // Table::new with strict = true
+Table::new(ddl, glob, on_file)      // on_file: Fn(&str) -> Vec<Row>, infallible
+Table::try_new(ddl, glob, on_file)  // on_file: Fn(&str) -> Result<Vec<Row>, _>
+Table::strict(ddl, glob, on_file)   // Table::new with strict = true
 ```
 
 :::
@@ -321,7 +327,7 @@ Maps files to table rows.
   `{name}` [captures](./columns.md#glob-captures). Every table whose glob
   matches a file receives that file's rows — a file can populate multiple
   tables.
-- `extract` — Callback receiving the matched file's full path (the root
+- `on_file` (`on_file` / `onFile`) — Callback receiving the matched file's full path (the root
   joined with the file's relative path — absolute when `root` is absolute)
   and returning the rows that file contributes. `dirsql` never reads file
   contents itself; a callback that needs the body reads the path. Return
@@ -356,7 +362,7 @@ relative to the root. Errors never terminate the stream.
 
 ## Value types
 
-An `extract` callback (and the SQLite columns it feeds) accepts:
+An `on_file` callback (and the SQLite columns it feeds) accepts:
 
 | SQLite column | Python value | TypeScript value | Rust `Value` |
 |---|---|---|---|

dirsql-0.3.99/packages/python/e2e-attestations/claude-open-issues-review-le8hm5-red-570.json

@@ -0,0 +1,7 @@
+{
+  "command": "uv run python -m pytest tests/e2e/ -x -q",
+  "ran_at": 1783948915,
+  "exit_code": 0,
+  "commit": "4c827cbcd164e9273c8738e95328dd88d4c2548f",
+  "branch": "claude/open-issues-review-le8hm5-red-570"
+}

{dirsql-0.3.97 → dirsql-0.3.99}/packages/python/src/lib.rs

@@ -1,7 +1,7 @@
 //! PyO3 binding for `dirsql`. Intentionally thin: all orchestration lives in
 //! `dirsql::DirSQL`. This layer only:
 //!
-//! - wraps a Python `extract` callable in a Rust closure (acquiring the GIL as
+//! - wraps a Python `on_file` callable in a Rust closure (acquiring the GIL as
 //!   needed) so it can be handed to [`dirsql::Table`]
 //! - converts row dicts, values, and events between Python and Rust
 //! - forwards `new` / `query` / `_start_watcher` / `_poll_events` to the
@@ -21,7 +21,7 @@ mod python {
     use std::time::Duration;
 
     /// A table definition. Mirrors `dirsql::Table` but holds a Python
-    /// callable for `extract`.
+    /// callable for `on_file`.
     #[pyclass(name = "Table", frozen)]
     struct PyTable {
         #[pyo3(get)]
@@ -29,7 +29,7 @@ mod python {
         #[pyo3(get)]
         glob: String,
         #[pyo3(get)]
-        extract: Py<PyAny>,
+        on_file: Py<PyAny>,
         #[pyo3(get)]
         strict: bool,
         /// Parsed table name (from `ddl`) via `dirsql::db::parse_table_name`,
@@ -44,13 +44,13 @@ mod python {
     #[pymethods]
     impl PyTable {
         #[new]
-        #[pyo3(signature = (*, ddl, glob, extract, strict=false))]
-        fn new(ddl: String, glob: String, extract: Py<PyAny>, strict: bool) -> Self {
+        #[pyo3(signature = (*, ddl, glob, on_file, strict=false))]
+        fn new(ddl: String, glob: String, on_file: Py<PyAny>, strict: bool) -> Self {
             let name = parse_table_name(&ddl);
             PyTable {
                 ddl,
                 glob,
-                extract,
+                on_file,
                 strict,
                 name,
             }
@@ -195,11 +195,11 @@ mod python {
     }
 
     fn build_table(py: Python<'_>, t: &PyTable) -> Table {
-        let extract_ref = t.extract.clone_ref(py);
+        let on_file_ref = t.on_file.clone_ref(py);
         let mut table = Table::try_new(
             t.ddl.clone(),
             t.glob.clone(),
-            make_extract_closure(extract_ref),
+            make_on_file_closure(on_file_ref),
         );
         table.strict = t.strict;
         table
@@ -207,23 +207,23 @@ mod python {
 
     type BoxError = Box<dyn std::error::Error + Send + Sync + 'static>;
 
-    fn make_extract_closure(
-        extract: Py<PyAny>,
+    fn make_on_file_closure(
+        on_file: Py<PyAny>,
     ) -> impl Fn(&str) -> std::result::Result<Vec<Row>, BoxError> + Send + Sync + 'static {
         move |path: &str| {
             Python::attach(|py| -> std::result::Result<Vec<Row>, BoxError> {
-                let result = extract
+                let result = on_file
                     .call1(py, (path,))
-                    .map_err(|e| -> BoxError { Box::new(ExtractError(e.to_string())) })?;
+                    .map_err(|e| -> BoxError { Box::new(OnFileError(e.to_string())) })?;
                 let raw: Vec<HashMap<String, Py<PyAny>>> = result
                     .extract(py)
-                    .map_err(|e: PyErr| -> BoxError { Box::new(ExtractError(e.to_string())) })?;
+                    .map_err(|e: PyErr| -> BoxError { Box::new(OnFileError(e.to_string())) })?;
 
                 let mut rows = Vec::with_capacity(raw.len());
                 for r in &raw {
                     rows.push(
                         convert_py_row(py, r)
-                            .map_err(|e| -> BoxError { Box::new(ExtractError(e.to_string())) })?,
+                            .map_err(|e| -> BoxError { Box::new(OnFileError(e.to_string())) })?,
                     );
                 }
                 Ok(rows)
@@ -232,13 +232,13 @@ mod python {
     }
 
     #[derive(Debug)]
-    struct ExtractError(String);
-    impl std::fmt::Display for ExtractError {
+    struct OnFileError(String);
+    impl std::fmt::Display for OnFileError {
         fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
             f.write_str(&self.0)
         }
     }
-    impl std::error::Error for ExtractError {}
+    impl std::error::Error for OnFileError {}
 
     fn to_py_err<E: std::fmt::Display>(e: E) -> PyErr {
         PyRuntimeError::new_err(e.to_string())
@@ -493,8 +493,8 @@ mod python {
         }
 
         #[test]
-        fn extract_error_displays_inner() {
-            assert_eq!(ExtractError("bad".to_string()).to_string(), "bad");
+        fn on_file_error_displays_inner() {
+            assert_eq!(OnFileError("bad".to_string()).to_string(), "bad");
         }
 
         #[test]

{dirsql-0.3.97 → dirsql-0.3.99}/packages/rust/docs/howto/embed.md

@@ -33,7 +33,7 @@ comments/t1/c2.json    # {"body": "nice post", "author": "bob"}
 comments/t2/c1.json    # {"body": "following up", "author": "alice"}
 ```
 
-Unlike a config-file table, a programmatic table takes an `extract`
+Unlike a config-file table, a programmatic table takes an `on_file`
 callback — your code reads each matched file and returns its rows, with
 [glob captures and stat columns](../reference/columns.md) merged on
 automatically (here, `{thread}` from the path):
@@ -47,7 +47,7 @@ import json
 from dirsql import DirSQL, Table
 
 
-def extract(path: str) -> list[dict]:
+def on_file(path: str) -> list[dict]:
     with open(path, encoding="utf-8") as f:
         return [json.load(f)]
 
@@ -59,7 +59,7 @@ async def main() -> None:
             Table(
                 ddl="CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
                 glob="comments/{thread}/*.json",
-                extract=extract,
+                on_file=on_file,
             )
         ],
     )
@@ -81,7 +81,7 @@ const db = new DirSQL({
     {
       ddl: "CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
       glob: "comments/{thread}/*.json",
-      extract: (path) => [JSON.parse(readFileSync(path, "utf8"))],
+      onFile: (path) => [JSON.parse(readFileSync(path, "utf8"))],
     },
   ],
 });
@@ -99,7 +99,7 @@ use std::collections::HashMap;
 
 use dirsql::{DirSQL, Table, Value};
 
-fn extract(path: &str) -> Vec<HashMap<String, Value>> {
+fn on_file(path: &str) -> Vec<HashMap<String, Value>> {
     let raw = std::fs::read_to_string(path).unwrap_or_default();
     let Ok(serde_json::Value::Object(obj)) = serde_json::from_str(&raw) else {
         return vec![];
@@ -119,7 +119,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
         .table(Table::new(
             "CREATE TABLE comments (thread TEXT, author TEXT, body TEXT)",
             "comments/{thread}/*.json",
-            extract,
+            on_file,
         ))
         .build()?;
 

{dirsql-0.3.97 → dirsql-0.3.99/packages/rust}/docs/howto/extract-from-contents.md

@@ -79,6 +79,6 @@ SQLite value mapping is under
   file. If it is expensive, [keep the index across restarts](./persist.md).
 - The flagship use of `on-file` — computing embeddings — is
   [Search documents by meaning](./search-by-meaning.md).
-- Embedding `dirsql` in a program instead? The SDK's `extract` callback
+- Embedding `dirsql` in a program instead? The SDK's `on_file` callback
   fills the same role in-process — see
   [Embed `dirsql` in your application](./embed.md).

{dirsql-0.3.97 → dirsql-0.3.99/packages/rust}/docs/index.md

@@ -20,7 +20,7 @@ But querying across many files is slow.
 
 ## Solution
 
-`dirsql` bridges this gap. The filesystem remains the source of truth, but you get SQL queries and real-time change events for free. Define tables with glob patterns and extract functions, and `dirsql` handles the rest.
+`dirsql` bridges this gap. The filesystem remains the source of truth, but you get SQL queries and real-time change events for free. Define tables with glob patterns and on-file callbacks, and `dirsql` handles the rest.
 
 ::: code-group
 
@@ -34,7 +34,7 @@ db = DirSQL(
         Table(
             ddl="CREATE TABLE files (name TEXT, size INTEGER, type TEXT)",
             glob="data/*.json",
-            extract=lambda path: [json.loads(open(path, encoding="utf-8").read())],
+            on_file=lambda path: [json.loads(open(path, encoding="utf-8").read())],
         ),
     ],
 )
@@ -70,7 +70,7 @@ const db = new DirSQL({
     new Table({
       ddl: 'CREATE TABLE files (name TEXT, size INTEGER, type TEXT)',
       glob: 'data/*.json',
-      extract: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
+      onFile: (path) => [JSON.parse(readFileSync(path, 'utf8'))],
     }),
   ],
 });