dirsql 0.4.61__tar.gz → 0.4.62__tar.gz

{dirsql-0.4.61 → dirsql-0.4.62}/Cargo.lock

@@ -552,7 +552,7 @@ checksum = "6184e33543162437515c2e2b48714794e37845ec9851711914eec9d308f6ebe8"
 
 [[package]]
 name = "dirsql"
-version = "0.4.61"
+version = "0.4.62"
 dependencies = [
  "assert_cmd",
  "axum",
@@ -600,7 +600,7 @@ dependencies = [
 
 [[package]]
 name = "dirsql-py-ext"
-version = "0.4.61"
+version = "0.4.62"
 dependencies = [
  "dirsql",
  "pyo3",

{dirsql-0.4.61 → dirsql-0.4.62}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dirsql
-Version: 0.4.61
+Version: 0.4.62
 Requires-Dist: bin-shim>=0.1
 Summary: Ephemeral SQL index over a local directory
 Keywords: sql,filesystem,directory,sqlite,index

{dirsql-0.4.61 → dirsql-0.4.62}/docs/getting-started.md

@@ -81,11 +81,15 @@ The first run downloads the package (`npx` asks for confirmation — answer
 `y`; `uvx` prints download progress), then prints the result:
 
 ```
-[{"files":3}]
+files
+-----
+3
+
+1 row
 ```
 
 Three files, three rows. That one command scanned the directory, handed
-SQLite one row per file, ran your SQL, and printed the answer as JSON.
+SQLite one row per file, ran your SQL, and printed the answer.
 
 There is no named table here — you never declared one. `'./'` is a
 [path-table](./reference/path-tables.md): a quoted path written where a table
@@ -94,8 +98,9 @@ in. The path *is* the query.
 
 ## 3. Select some columns
 
-The response is always a JSON array of row objects, so from here on we pipe
-it through `jq` to pretty-print. Ask for two columns instead of a count:
+At a terminal `dirsql` prints a table; when its output is piped, it prints a
+JSON array of row objects instead. From here on we pipe it through `jq` to
+pretty-print. Ask for two columns instead of a count:
 
 ::: code-group
 

{dirsql-0.4.61/packages/rust → dirsql-0.4.62}/docs/howto/write-a-plugin.md

@@ -60,11 +60,12 @@ its `embed()` SQL function),
 and [`ignore`](../reference/config.md#dirsql-keys).
 
 There are **no plugin-specific keys and no plugin-specific restrictions**. The
-config schema is content-only: the index `root` and `--persist` are
-[runner-owned flags](../reference/config.md#dirsql-keys) (`--root`, `--persist
-[PATH]`), decided by whoever runs `dirsql`, never by a config file — so a
-plugin has nothing to say about them. Whatever you can put in your own
-`.dirsql.toml`, a plugin can put in its fragment, and vice-versa.
+config schema is content-only: the index root and persistence are
+[runner-owned](../reference/config.md#dirsql-keys) — the root is the directory
+`dirsql` is run from (or an SDK's explicit `root`), persistence is the
+`--persist [PATH]` flag — decided by whoever runs `dirsql`, never by a config
+file, so a plugin has nothing to say about them. Whatever you can put in your
+own `.dirsql.toml`, a plugin can put in its fragment, and vice-versa.
 
 ## Hook commands
 

{dirsql-0.4.61/packages/rust → dirsql-0.4.62}/docs/plugins.md

@@ -93,9 +93,10 @@ scope.
 ### Vector cache
 
 Computed vectors are cached at `~/.cache/dirsql/embeddings/` (respecting
-`XDG_CACHE_HOME`), keyed on the SHA-256 of the value bytes plus the model
-identifier. Changing either recomputes — switching models never serves stale
-vectors — and re-running a query over unchanged files is cache hits all the
-way. There is no eviction: the directory is **safe to wipe at any time**; the
-only cost is re-embedding. The cache never lives inside a queried tree — the
-worker writes nothing into the directories you query.
+`XDG_CACHE_HOME`): one SQLite database per model identifier, each row keyed
+on the SHA-256 of the value bytes. Changing the value or the model recomputes
+— switching models never serves stale vectors — and re-running a query over
+unchanged files is cache hits all the way, a whole batch answered by one
+query. There is no eviction: the directory is **safe to wipe at any time**;
+the only cost is re-embedding. The cache never lives inside a queried tree —
+the worker writes nothing into the directories you query.

{dirsql-0.4.61 → dirsql-0.4.62}/docs/reference/cli.md

@@ -1,11 +1,13 @@
 # CLI
 
-Query is the default: `dirsql "<sql>"` runs one query and prints JSON rows.
+Query is the default: `dirsql "<sql>"` runs one query and prints the rows —
+a table at a terminal, a JSON array when piped (see
+[Output format](#output-format)).
 The `dirsql` binary has these modes:
 
 | Invocation | Behavior |
 |---|---|
-| `dirsql "<sql>"` | Run one query over the directory and print the rows as JSON. The default; identical to `dirsql query "<sql>"`. |
+| `dirsql "<sql>"` | Run one query over the directory and print the rows. The default; identical to `dirsql query "<sql>"`. |
 | `dirsql query "<sql>"` | Explicit synonym for the default one-shot query. |
 | `dirsql server` | Start a long-lived HTTP server exposing a SQL view of a directory. See [HTTP API](./http-api.md). |
 | `dirsql init` | Generate a `.dirsql.toml`. |
@@ -53,7 +55,7 @@ pipeline, same flags, same output. See that section for config discovery,
 
 ```bash
 dirsql
-# dirsql 0.2.7 — this directory is a database.
+# dirsql <version> — this directory is a database.
 #
 #   SELECT basename, size FROM './' ORDER BY size DESC LIMIT 5;
 #   SELECT path FROM './**/*.md' WHERE content LIKE '%TODO%';
@@ -331,9 +333,10 @@ is a hard error — `error: the subcommand 'query' cannot be used with
 for the server they follow the subcommand: `dirsql server -c <cfg>`.)
 :::
 
-The subcommand builds the index, runs the SQL, prints the result rows as a
-JSON array on stdout (byte-identical to the [`POST /query`](./http-api.md)
-response body), and exits `0`.
+The subcommand builds the index, runs the SQL, prints the result rows on
+stdout — a table at a terminal, otherwise a JSON array byte-identical to the
+[`POST /query`](./http-api.md) response body (see
+[Output format](#output-format)) — and exits `0`.
 
 `dirsql query` is a thin adapter over the **same query pipeline the server
 uses**, so behavior is identical to `POST /query` by construction:
@@ -413,7 +416,7 @@ The output does **not** auto-load. Once you've tweaked it, pass it explicitly
 to run against it:
 
 ```bash
-dirsql "SELECT * FROM files" -c ./.dirsql.toml
+dirsql "SELECT * FROM records" -c ./.dirsql.toml
 ```
 
 ### Flags

{dirsql-0.4.61 → dirsql-0.4.62}/docs/reference/sdk.md

@@ -54,6 +54,7 @@ DirSQL(
     *,
     tables: list[Table] | None = None,
     ignore: list[str] | None = None,
+    no_ignore: bool = False,
     config: str | list[str] | None = None,
     persist: bool = False,
     persist_path: str | None = None,
@@ -68,6 +69,7 @@ new DirSQL({
     root?: string,
     tables?: TableDef[],
     ignore?: string[],
+    noIgnore?: boolean,
     config?: string | string[],
     persist?: boolean,
     persistPath?: string,
@@ -80,6 +82,7 @@ DirSQL::builder()
     .root(root)                     // optional
     .tables(tables)                 // optional; append one with .table(t)
     .ignore(patterns)               // optional
+    .no_ignore(true)                // optional; default false
     .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
@@ -115,6 +118,10 @@ shortcut was removed in #603 — use
 - `tables` — Programmatic [`Table`](#table) definitions.
 - `ignore` — Glob patterns matched against root-relative paths; matched
   files are skipped entirely (scan and watch).
+- `no_ignore` / `noIgnore` — Scan files a `.gitignore` would hide.
+  [Path-tables](./path-tables.md#skip-rules) respect `.gitignore` files by
+  default; the built-in `node_modules`/`.git` skips and any `ignore` patterns
+  still apply. The CLI's [`--no-ignore`](./cli.md#flags).
 - `config` — Path to a [`.dirsql.toml`](./config.md). Its `[[table]]`
   entries are appended after any programmatic `tables`; its `ignore`
   patterns and `[[dirsql.extension]]` entries are appended likewise. The

{dirsql-0.4.61 → dirsql-0.4.62}/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 = "0.4.61"
+version = "0.4.62"
 # abi3 note: the `abi3-py310` pyo3 feature (below) builds ONE stable-ABI
 # `cp310-abi3` wheel per platform that loads on every CPython >= 3.10
 # (matching `pyproject.toml`'s `requires-python = ">=3.10"`), instead of

{dirsql-0.4.61/packages/rust → dirsql-0.4.62/packages/python}/docs/getting-started.md

@@ -81,11 +81,15 @@ The first run downloads the package (`npx` asks for confirmation — answer
 `y`; `uvx` prints download progress), then prints the result:
 
 ```
-[{"files":3}]
+files
+-----
+3
+
+1 row
 ```
 
 Three files, three rows. That one command scanned the directory, handed
-SQLite one row per file, ran your SQL, and printed the answer as JSON.
+SQLite one row per file, ran your SQL, and printed the answer.
 
 There is no named table here — you never declared one. `'./'` is a
 [path-table](./reference/path-tables.md): a quoted path written where a table
@@ -94,8 +98,9 @@ in. The path *is* the query.
 
 ## 3. Select some columns
 
-The response is always a JSON array of row objects, so from here on we pipe
-it through `jq` to pretty-print. Ask for two columns instead of a count:
+At a terminal `dirsql` prints a table; when its output is piped, it prints a
+JSON array of row objects instead. From here on we pipe it through `jq` to
+pretty-print. Ask for two columns instead of a count:
 
 ::: code-group
 

{dirsql-0.4.61 → dirsql-0.4.62}/packages/python/docs/howto/write-a-plugin.md

@@ -60,11 +60,12 @@ its `embed()` SQL function),
 and [`ignore`](../reference/config.md#dirsql-keys).
 
 There are **no plugin-specific keys and no plugin-specific restrictions**. The
-config schema is content-only: the index `root` and `--persist` are
-[runner-owned flags](../reference/config.md#dirsql-keys) (`--root`, `--persist
-[PATH]`), decided by whoever runs `dirsql`, never by a config file — so a
-plugin has nothing to say about them. Whatever you can put in your own
-`.dirsql.toml`, a plugin can put in its fragment, and vice-versa.
+config schema is content-only: the index root and persistence are
+[runner-owned](../reference/config.md#dirsql-keys) — the root is the directory
+`dirsql` is run from (or an SDK's explicit `root`), persistence is the
+`--persist [PATH]` flag — decided by whoever runs `dirsql`, never by a config
+file, so a plugin has nothing to say about them. Whatever you can put in your
+own `.dirsql.toml`, a plugin can put in its fragment, and vice-versa.
 
 ## Hook commands
 

{dirsql-0.4.61 → dirsql-0.4.62}/packages/python/docs/plugins.md

@@ -93,9 +93,10 @@ scope.
 ### Vector cache
 
 Computed vectors are cached at `~/.cache/dirsql/embeddings/` (respecting
-`XDG_CACHE_HOME`), keyed on the SHA-256 of the value bytes plus the model
-identifier. Changing either recomputes — switching models never serves stale
-vectors — and re-running a query over unchanged files is cache hits all the
-way. There is no eviction: the directory is **safe to wipe at any time**; the
-only cost is re-embedding. The cache never lives inside a queried tree — the
-worker writes nothing into the directories you query.
+`XDG_CACHE_HOME`): one SQLite database per model identifier, each row keyed
+on the SHA-256 of the value bytes. Changing the value or the model recomputes
+— switching models never serves stale vectors — and re-running a query over
+unchanged files is cache hits all the way, a whole batch answered by one
+query. There is no eviction: the directory is **safe to wipe at any time**;
+the only cost is re-embedding. The cache never lives inside a queried tree —
+the worker writes nothing into the directories you query.

{dirsql-0.4.61/packages/rust → dirsql-0.4.62/packages/python}/docs/reference/cli.md

@@ -1,11 +1,13 @@
 # CLI
 
-Query is the default: `dirsql "<sql>"` runs one query and prints JSON rows.
+Query is the default: `dirsql "<sql>"` runs one query and prints the rows —
+a table at a terminal, a JSON array when piped (see
+[Output format](#output-format)).
 The `dirsql` binary has these modes:
 
 | Invocation | Behavior |
 |---|---|
-| `dirsql "<sql>"` | Run one query over the directory and print the rows as JSON. The default; identical to `dirsql query "<sql>"`. |
+| `dirsql "<sql>"` | Run one query over the directory and print the rows. The default; identical to `dirsql query "<sql>"`. |
 | `dirsql query "<sql>"` | Explicit synonym for the default one-shot query. |
 | `dirsql server` | Start a long-lived HTTP server exposing a SQL view of a directory. See [HTTP API](./http-api.md). |
 | `dirsql init` | Generate a `.dirsql.toml`. |
@@ -53,7 +55,7 @@ pipeline, same flags, same output. See that section for config discovery,
 
 ```bash
 dirsql
-# dirsql 0.2.7 — this directory is a database.
+# dirsql <version> — this directory is a database.
 #
 #   SELECT basename, size FROM './' ORDER BY size DESC LIMIT 5;
 #   SELECT path FROM './**/*.md' WHERE content LIKE '%TODO%';
@@ -331,9 +333,10 @@ is a hard error — `error: the subcommand 'query' cannot be used with
 for the server they follow the subcommand: `dirsql server -c <cfg>`.)
 :::
 
-The subcommand builds the index, runs the SQL, prints the result rows as a
-JSON array on stdout (byte-identical to the [`POST /query`](./http-api.md)
-response body), and exits `0`.
+The subcommand builds the index, runs the SQL, prints the result rows on
+stdout — a table at a terminal, otherwise a JSON array byte-identical to the
+[`POST /query`](./http-api.md) response body (see
+[Output format](#output-format)) — and exits `0`.
 
 `dirsql query` is a thin adapter over the **same query pipeline the server
 uses**, so behavior is identical to `POST /query` by construction:
@@ -413,7 +416,7 @@ The output does **not** auto-load. Once you've tweaked it, pass it explicitly
 to run against it:
 
 ```bash
-dirsql "SELECT * FROM files" -c ./.dirsql.toml
+dirsql "SELECT * FROM records" -c ./.dirsql.toml
 ```
 
 ### Flags

{dirsql-0.4.61/packages/rust → dirsql-0.4.62/packages/python}/docs/reference/sdk.md

@@ -54,6 +54,7 @@ DirSQL(
     *,
     tables: list[Table] | None = None,
     ignore: list[str] | None = None,
+    no_ignore: bool = False,
     config: str | list[str] | None = None,
     persist: bool = False,
     persist_path: str | None = None,
@@ -68,6 +69,7 @@ new DirSQL({
     root?: string,
     tables?: TableDef[],
     ignore?: string[],
+    noIgnore?: boolean,
     config?: string | string[],
     persist?: boolean,
     persistPath?: string,
@@ -80,6 +82,7 @@ DirSQL::builder()
     .root(root)                     // optional
     .tables(tables)                 // optional; append one with .table(t)
     .ignore(patterns)               // optional
+    .no_ignore(true)                // optional; default false
     .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
@@ -115,6 +118,10 @@ shortcut was removed in #603 — use
 - `tables` — Programmatic [`Table`](#table) definitions.
 - `ignore` — Glob patterns matched against root-relative paths; matched
   files are skipped entirely (scan and watch).
+- `no_ignore` / `noIgnore` — Scan files a `.gitignore` would hide.
+  [Path-tables](./path-tables.md#skip-rules) respect `.gitignore` files by
+  default; the built-in `node_modules`/`.git` skips and any `ignore` patterns
+  still apply. The CLI's [`--no-ignore`](./cli.md#flags).
 - `config` — Path to a [`.dirsql.toml`](./config.md). Its `[[table]]`
   entries are appended after any programmatic `tables`; its `ignore`
   patterns and `[[dirsql.extension]]` entries are appended likewise. The

dirsql-0.4.62/packages/python/e2e-attestations/claude-1196-join-index.json

@@ -0,0 +1,7 @@
+{
+  "command": "just test-e2e",
+  "ran_at": 1790959572,
+  "exit_code": 0,
+  "commit": "16f02f05e5f6ca5fc06ad5ce716fae9d1ce78bc5",
+  "branch": "claude/1196-join-index"
+}

dirsql-0.4.62/packages/python/e2e-attestations/claude-1226-stale-docs.json

@@ -0,0 +1,7 @@
+{
+  "command": "just test-e2e",
+  "ran_at": 1790960011,
+  "exit_code": 0,
+  "commit": "b36c8055c086002c81314daa2d7e34cded58b561",
+  "branch": "claude/1226-stale-docs"
+}

{dirsql-0.4.61 → dirsql-0.4.62}/packages/rust/Cargo.toml

@@ -6,7 +6,7 @@ description = "Ephemeral SQL index over a local directory"
 # version stays for the binding crates (publish = false). The literal
 # intentionally lags the published version: putitoutthere rewrites it to
 # the planned release version at build time and never commits it back.
-version = "0.4.61"
+version = "0.4.62"
 edition.workspace = true
 # Literal `license` (not `license.workspace = true`) because
 # putitoutthere's preflight check reads `[package].license` directly

{dirsql-0.4.61/packages/python → dirsql-0.4.62/packages/rust}/docs/getting-started.md

@@ -81,11 +81,15 @@ The first run downloads the package (`npx` asks for confirmation — answer
 `y`; `uvx` prints download progress), then prints the result:
 
 ```
-[{"files":3}]
+files
+-----
+3
+
+1 row
 ```
 
 Three files, three rows. That one command scanned the directory, handed
-SQLite one row per file, ran your SQL, and printed the answer as JSON.
+SQLite one row per file, ran your SQL, and printed the answer.
 
 There is no named table here — you never declared one. `'./'` is a
 [path-table](./reference/path-tables.md): a quoted path written where a table
@@ -94,8 +98,9 @@ in. The path *is* the query.
 
 ## 3. Select some columns
 
-The response is always a JSON array of row objects, so from here on we pipe
-it through `jq` to pretty-print. Ask for two columns instead of a count:
+At a terminal `dirsql` prints a table; when its output is piped, it prints a
+JSON array of row objects instead. From here on we pipe it through `jq` to
+pretty-print. Ask for two columns instead of a count:
 
 ::: code-group
 

{dirsql-0.4.61 → dirsql-0.4.62/packages/rust}/docs/howto/write-a-plugin.md

@@ -60,11 +60,12 @@ its `embed()` SQL function),
 and [`ignore`](../reference/config.md#dirsql-keys).
 
 There are **no plugin-specific keys and no plugin-specific restrictions**. The
-config schema is content-only: the index `root` and `--persist` are
-[runner-owned flags](../reference/config.md#dirsql-keys) (`--root`, `--persist
-[PATH]`), decided by whoever runs `dirsql`, never by a config file — so a
-plugin has nothing to say about them. Whatever you can put in your own
-`.dirsql.toml`, a plugin can put in its fragment, and vice-versa.
+config schema is content-only: the index root and persistence are
+[runner-owned](../reference/config.md#dirsql-keys) — the root is the directory
+`dirsql` is run from (or an SDK's explicit `root`), persistence is the
+`--persist [PATH]` flag — decided by whoever runs `dirsql`, never by a config
+file, so a plugin has nothing to say about them. Whatever you can put in your
+own `.dirsql.toml`, a plugin can put in its fragment, and vice-versa.
 
 ## Hook commands
 

{dirsql-0.4.61 → dirsql-0.4.62/packages/rust}/docs/plugins.md

@@ -93,9 +93,10 @@ scope.
 ### Vector cache
 
 Computed vectors are cached at `~/.cache/dirsql/embeddings/` (respecting
-`XDG_CACHE_HOME`), keyed on the SHA-256 of the value bytes plus the model
-identifier. Changing either recomputes — switching models never serves stale
-vectors — and re-running a query over unchanged files is cache hits all the
-way. There is no eviction: the directory is **safe to wipe at any time**; the
-only cost is re-embedding. The cache never lives inside a queried tree — the
-worker writes nothing into the directories you query.
+`XDG_CACHE_HOME`): one SQLite database per model identifier, each row keyed
+on the SHA-256 of the value bytes. Changing the value or the model recomputes
+— switching models never serves stale vectors — and re-running a query over
+unchanged files is cache hits all the way, a whole batch answered by one
+query. There is no eviction: the directory is **safe to wipe at any time**;
+the only cost is re-embedding. The cache never lives inside a queried tree —
+the worker writes nothing into the directories you query.

{dirsql-0.4.61/packages/python → dirsql-0.4.62/packages/rust}/docs/reference/cli.md

@@ -1,11 +1,13 @@
 # CLI
 
-Query is the default: `dirsql "<sql>"` runs one query and prints JSON rows.
+Query is the default: `dirsql "<sql>"` runs one query and prints the rows —
+a table at a terminal, a JSON array when piped (see
+[Output format](#output-format)).
 The `dirsql` binary has these modes:
 
 | Invocation | Behavior |
 |---|---|
-| `dirsql "<sql>"` | Run one query over the directory and print the rows as JSON. The default; identical to `dirsql query "<sql>"`. |
+| `dirsql "<sql>"` | Run one query over the directory and print the rows. The default; identical to `dirsql query "<sql>"`. |
 | `dirsql query "<sql>"` | Explicit synonym for the default one-shot query. |
 | `dirsql server` | Start a long-lived HTTP server exposing a SQL view of a directory. See [HTTP API](./http-api.md). |
 | `dirsql init` | Generate a `.dirsql.toml`. |
@@ -53,7 +55,7 @@ pipeline, same flags, same output. See that section for config discovery,
 
 ```bash
 dirsql
-# dirsql 0.2.7 — this directory is a database.
+# dirsql <version> — this directory is a database.
 #
 #   SELECT basename, size FROM './' ORDER BY size DESC LIMIT 5;
 #   SELECT path FROM './**/*.md' WHERE content LIKE '%TODO%';
@@ -331,9 +333,10 @@ is a hard error — `error: the subcommand 'query' cannot be used with
 for the server they follow the subcommand: `dirsql server -c <cfg>`.)
 :::
 
-The subcommand builds the index, runs the SQL, prints the result rows as a
-JSON array on stdout (byte-identical to the [`POST /query`](./http-api.md)
-response body), and exits `0`.
+The subcommand builds the index, runs the SQL, prints the result rows on
+stdout — a table at a terminal, otherwise a JSON array byte-identical to the
+[`POST /query`](./http-api.md) response body (see
+[Output format](#output-format)) — and exits `0`.
 
 `dirsql query` is a thin adapter over the **same query pipeline the server
 uses**, so behavior is identical to `POST /query` by construction:
@@ -413,7 +416,7 @@ The output does **not** auto-load. Once you've tweaked it, pass it explicitly
 to run against it:
 
 ```bash
-dirsql "SELECT * FROM files" -c ./.dirsql.toml
+dirsql "SELECT * FROM records" -c ./.dirsql.toml
 ```
 
 ### Flags

{dirsql-0.4.61/packages/python → dirsql-0.4.62/packages/rust}/docs/reference/sdk.md

@@ -54,6 +54,7 @@ DirSQL(
     *,
     tables: list[Table] | None = None,
     ignore: list[str] | None = None,
+    no_ignore: bool = False,
     config: str | list[str] | None = None,
     persist: bool = False,
     persist_path: str | None = None,
@@ -68,6 +69,7 @@ new DirSQL({
     root?: string,
     tables?: TableDef[],
     ignore?: string[],
+    noIgnore?: boolean,
     config?: string | string[],
     persist?: boolean,
     persistPath?: string,
@@ -80,6 +82,7 @@ DirSQL::builder()
     .root(root)                     // optional
     .tables(tables)                 // optional; append one with .table(t)
     .ignore(patterns)               // optional
+    .no_ignore(true)                // optional; default false
     .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
@@ -115,6 +118,10 @@ shortcut was removed in #603 — use
 - `tables` — Programmatic [`Table`](#table) definitions.
 - `ignore` — Glob patterns matched against root-relative paths; matched
   files are skipped entirely (scan and watch).
+- `no_ignore` / `noIgnore` — Scan files a `.gitignore` would hide.
+  [Path-tables](./path-tables.md#skip-rules) respect `.gitignore` files by
+  default; the built-in `node_modules`/`.git` skips and any `ignore` patterns
+  still apply. The CLI's [`--no-ignore`](./cli.md#flags).
 - `config` — Path to a [`.dirsql.toml`](./config.md). Its `[[table]]`
   entries are appended after any programmatic `tables`; its `ignore`
   patterns and `[[dirsql.extension]]` entries are appended likewise. The

{dirsql-0.4.61 → dirsql-0.4.62}/packages/rust/src/cli/run.rs

@@ -33,7 +33,8 @@ use serde_json::Value;
              bare `dirsql` opens a REPL; `dirsql server` starts the HTTP \
              server.",
     long_about = "Runs one SQL query over a local directory and prints the \
-                  result rows as JSON. `dirsql \"SELECT * FROM './'\"` is the \
+                  result rows: a table on a terminal, a JSON array when \
+                  piped. `dirsql \"SELECT * FROM './'\"` is the \
                   default; `dirsql query \"<sql>\"` is an explicit synonym. \
                   With no subcommand and no SQL, dirsql reads statements until \
                   EOF instead: a prompted REPL on a terminal, one statement \
@@ -47,8 +48,9 @@ use serde_json::Value;
                   subcommand-local: for `query`/`server` pass them AFTER the \
                   subcommand (`dirsql query <sql> -c <cfg>`); a flag before a \
                   subcommand is a hard error. The `init` subcommand writes a \
-                  starter `.dirsql.toml` defining a `files` table — no \
-                  target-directory inspection, no network, deterministic.",
+                  starter `.dirsql.toml` defining a `records` table over \
+                  `**/*.json` — no target-directory inspection, no network, \
+                  deterministic.",
     args_conflicts_with_subcommands = true
 )]
 struct Cli {
@@ -151,14 +153,15 @@ impl ConfigArgs {
 
 #[derive(Debug, Subcommand)]
 enum Command {
-    /// Write the fixed starter `.dirsql.toml` — a `files` table over every
-    /// file in the directory. The output does not auto-load; pass it with
-    /// `dirsql query <sql> -c ./.dirsql.toml`. No target-directory
-    /// inspection.
+    /// Write the fixed starter `.dirsql.toml` — a `records` table over
+    /// `**/*.json`, parsed by an `on-file` hook. The output does not
+    /// auto-load; pass it with `dirsql query <sql> -c ./.dirsql.toml`. No
+    /// target-directory inspection.
     Init(InitArgs),
 
     /// Run one SQL query against the indexed directory, print the result
-    /// rows as JSON on stdout, and exit. No server, no watch. This is the
+    /// rows on stdout (a table on a terminal, a JSON array when piped), and
+    /// exit. No server, no watch. This is the
     /// explicit synonym for the default `dirsql "<sql>"`. Shares the
     /// server's query pipeline, so config loading, hooks, the read-only
     /// rule, and error classification are identical to `POST /query`.

{dirsql-0.4.61 → dirsql-0.4.62}/packages/rust/src/vtab.rs

@@ -39,6 +39,10 @@ const CTIME_COLUMN: usize = 6;
 /// Column index of the lazily-read `content`, which follows the stat columns.
 const CONTENT_COLUMN: usize = STAT_COLUMNS.len();
 
+/// `path`, `basename` and `dir`: the columns a join between two path-tables
+/// is written on, answered by lookup rather than a rescan of the inner glob.
+const LOOKUP_COLUMNS: [usize; 3] = [PATH_COLUMN, BASENAME_COLUMN, DIR_COLUMN];
+
 /// Schema a path-table declares to SQLite.
 ///
 /// `content` is declared last and `HIDDEN` so SQLite excludes it from
@@ -278,6 +282,8 @@ impl TableSource for ScanSpec {
 
     const NAME: &'static str = MODULE_NAME;
 
+    const LOOKUP_COLUMNS: &'static [usize] = &LOOKUP_COLUMNS;
+
     fn connect(args: &[&[u8]]) -> Result<(String, Self)> {
         Ok((declared_schema(), parse_module_args(args)?))
     }
@@ -309,6 +315,15 @@ impl TableSource for ScanSpec {
             None => ctx.set_result(&read_text(&self.root.join(&row.rel))),
         }
     }
+
+    fn lookup_key<'r>(&self, row: &'r FileRow, column: usize) -> Option<&'r str> {
+        match column {
+            PATH_COLUMN => Some(&row.path),
+            BASENAME_COLUMN => row.basename(),
+            DIR_COLUMN => row.dir(),
+            _ => None,
+        }
+    }
 }
 
 /// Register the path-table module on `conn`. Its tables hold the rows of the
@@ -571,6 +586,29 @@ mod tests {
         assert_eq!(cell(&row, -1), Some(ValueRef::Null));
     }
 
+    #[test]
+    fn lookup_columns_are_path_basename_and_dir_in_that_order() {
+        let names: Vec<&str> = LOOKUP_COLUMNS.iter().map(|c| STAT_COLUMNS[*c]).collect();
+        assert_eq!(names, ["path", "basename", "dir"]);
+    }
+
+    #[test]
+    fn a_scan_spec_keys_a_row_by_the_text_of_the_lookup_column() {
+        let args = args_with(&[b"'/tmp/notes'", b"'**/*.md'", b"''", b"'gitignore'"]);
+        let spec = parse_module_args(&args).unwrap();
+        let mut row = row_for("", "docs/a.md");
+        row.facts = facts(3);
+
+        assert_eq!(spec.lookup_key(&row, 0), Some("docs/a.md"));
+        assert_eq!(spec.lookup_key(&row, 1), Some("a.md"));
+        assert_eq!(spec.lookup_key(&row, 2), Some("docs"));
+        assert_eq!(
+            spec.lookup_key(&row, 4),
+            None,
+            "size is not a lookup column"
+        );
+    }
+
     #[test]
     fn chunks_cut_in_order_with_the_remainder_last() {
         assert_eq!(