pkgmap-py 0.1.0__tar.gz → 0.2.0__tar.gz

{pkgmap_py-0.1.0 → pkgmap_py-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pkgmap-py
-Version: 0.1.0
+Version: 0.2.0
 Summary: Cross-distribution Linux package name resolution
 Author: Levizor
 Author-email: Levizor <levizor@disroot.org>
@@ -19,7 +19,10 @@ Cross-distribution Linux package name resolution.
 
 Different distributions often package the exact same software under different names (for example, `ninja` on Arch is `ninja-build` on Debian and Alpine; `bat` on Arch is `rust-bat` on Debian and Fedora; `fd` on Arch is `rust-fd-find` on Debian; Nixpkgs uses specific attribute paths). `pkgmap` provides an offline SQLite database and a companion Python library/CLI to translate package names between any pair of Linux distributions, resolve packages across all repositories, or look up native packages by upstream project name.
 
-Data is updated daily from [Repology](https://repology.org) and indexed for instant local lookups. On first run, `pkgmap` automatically downloads and decompresses the latest daily database release (`~/.cache/pkgmap/pkgmap.db`).
+Data is updated daily from [Repology](https://repology.org) and indexed for instant local lookups. On first run, `pkgmap` automatically downloads and decompresses the latest daily database snapshot (`~/.cache/pkgmap/`).
+
+- **PyPI**: [`pkgmap-py`](https://pypi.org/project/pkgmap-py/)
+- **Web Interface**: [levizor.github.io/pkgmap](https://levizor.github.io/pkgmap/) (runs 100% client-side via SQLite WebAssembly + OPFS)
 
 ---
 
@@ -32,13 +35,28 @@ Use `--from` (`-f`) and `--to` (`-t`):
 ```bash
 # What is Arch's 'bat' called in Debian?
 pkgmap resolve bat --from arch --to debian
-# Output: rust-bat (0.22.1) [category: misc]
+# Output: rust-bat (0.24.0)
 
 # What is Arch's 'fd' in Nixpkgs?
 pkgmap resolve fd -f arch -t nixpkgs
 # Output: fd (10.5.0)
 ```
 
+### Batch resolution
+
+Pass multiple package names to resolve them in a single query:
+
+```bash
+pkgmap resolve git gcc bat --from nix --to gnuguix
+```
+
+Output:
+```text
+git -> git (2.54.0)
+gcc -> gcc (15.2.0)
+bat -> bat (0.26.1)
+```
+
 ### Resolve across all distributions
 
 Omit `--to` to see equivalents across every indexed distribution:
@@ -49,8 +67,8 @@ pkgmap resolve bat --from arch
 
 Output:
 ```text
-alpine_3_20: bat (0.24.0)
-debian_12: rust-bat (0.22.1) [category: misc]
+alpine_edge: bat (0.24.0)
+debian_unstable: rust-bat (0.24.0)
 fedora_rawhide: rust-bat (0.26.1)
 nix_unstable: bat (0.26.1)
 ubuntu_24_04: rust-bat (0.24.0)
@@ -63,7 +81,7 @@ Omit `--from` (or pass `--project` / `-p`) to resolve packages directly from an
 
 ```bash
 pkgmap resolve ripgrep --to debian
-# Output: rust-ripgrep (13.0.0) [category: misc]
+# Output: rust-ripgrep (14.1.0)
 ```
 
 ### JSON output
@@ -78,15 +96,15 @@ pkgmap resolve bat -f arch -t debian --json
 [
   {
     "name": "rust-bat",
-    "version": "0.22.1",
-    "category": "misc",
-    "repo": "debian_12",
-    "repo_family": "debuntu",
-    "install_name": "rust-bat"
+    "version": "0.24.0",
+    "repo": "debian_unstable",
+    "repo_family": "debuntu"
   }
 ]
 ```
 
+When multiple packages are passed with `--json`, the output is a dictionary keyed by each input package name.
+
 ### Other commands
 
 ```bash
@@ -95,27 +113,47 @@ pkgmap repos
 
 # Manually refresh the local database snapshot
 pkgmap update
+
+# Download the full database (all 330+ Repology repositories)
+pkgmap update --full
 ```
 
 ---
 
+## Core vs. Full Database Variants
+
+`pkgmap` publishes two database snapshots with every daily release:
+
+| Variant | File | Compressed Size | Coverage | Default For |
+| :--- | :--- | :--- | :--- | :--- |
+| **Core** | `pkgmap-core.db` | ~7 MB | Top 10 repositories (Nixpkgs, Arch, AUR, Debian, Ubuntu, Fedora, Alpine, openSUSE, Gentoo, Void) | **CLI & Web UI** |
+| **Full** | `pkgmap.db` | ~37 MB | All 330+ Repology repositories | **Python Library** |
+
+- **CLI behavior**: Defaults to the **Core** database (`~/.cache/pkgmap/pkgmap-core.db`) unless the Full database is already downloaded locally or `--full` is passed. If you query a repository not present in Core, the CLI prompts you to run `pkgmap update --full`. You can also pass `--core` or `--full` to any CLI command (`resolve`, `update`, `repos`).
+- **Python library behavior**: Defaults to the **Full** database (`~/.cache/pkgmap/pkgmap.db`). Call `set_default_variant("core")` (or set `PKGMAP_DB_VARIANT=core`) to use the Core database instead.
+
+---
+
 ## Python API
 
-You can also use `pkgmap` as a Python library:
+You can use `pkgmap` as a Python library:
 
 ```python
-from pkgmap import resolve, resolve_all, resolve_batch
+from pkgmap import resolve, resolve_all, resolve_batch, set_default_variant
+
+# Optional: switch library default from 'full' to 'core'
+# set_default_variant("core")
 
 # 1. Single package resolution
 res = resolve("bat", from_repo="arch", to_repo="debian")
 if res:
-    print(res.install_name, res.version)
-    # Output: rust-bat 0.22.1
+    print(res.name, res.version)
+    # Output: rust-bat 0.24.0
 
 # 2. Query all repositories for equivalents
 matches = resolve_all("bat", from_repo="arch")
 for r in matches:
-    print(f"{r.repo}: {r.install_name}")
+    print(f"{r.repo}: {r.name}")
 
 # 3. High-performance batch resolution (executed in a single SQL query)
 packages = ["bat", "fd", "ripgrep"]
@@ -123,7 +161,7 @@ results = resolve_batch(packages, from_repo="arch", to_repo="nixpkgs")
 
 for pkg, match in results.items():
     if match:
-        print(f"{pkg} -> {match.install_name}")
+        print(f"{pkg} -> {match.name}")
 ```
 
 ### API Methods
@@ -133,20 +171,24 @@ for pkg, match in results.items():
 - `resolve_batch(packages, from_repo=None, to_repo=None, db_path=None)`: Resolves a sequence of packages in a single batch query, returning `{package: PackageResolution | None}`.
 - `resolve_batch_all(packages, from_repo=None, to_repo=None, db_path=None)`: Batch resolution returning `{package: list[PackageResolution]}`.
 - `list_repositories(db_path=None)`: Returns all repositories with package counts and families.
+- `set_default_variant(variant)`: Sets the default database variant (`"full"` or `"core"`).
+- `get_default_variant()`: Returns the active default database variant.
 
 ---
 
 ## Configuration
 
-By default, the database is stored at:
-- `~/.cache/pkgmap/pkgmap.db`
+By default, databases are cached at:
+- Full database: `~/.cache/pkgmap/pkgmap.db`
+- Core database: `~/.cache/pkgmap/pkgmap-core.db`
 
-You can customize the location using:
-- The `PKGMAP_DB_PATH` environment variable:
+You can customize behavior using environment variables:
+- `PKGMAP_DB_VARIANT`: Set to `core` or `full` to override the default database variant.
+- `PKGMAP_DB_PATH`: Override the database file path directly:
   ```bash
   export PKGMAP_DB_PATH="/path/to/custom/pkgmap.db"
   ```
-- Or the `--db-path` argument on the CLI / `db_path` parameter in Python.
+- Or pass `--db-path` on the CLI / `db_path` in Python.
 
 ---
 

{pkgmap_py-0.1.0 → pkgmap_py-0.2.0}/README.md

@@ -4,7 +4,10 @@ Cross-distribution Linux package name resolution.
 
 Different distributions often package the exact same software under different names (for example, `ninja` on Arch is `ninja-build` on Debian and Alpine; `bat` on Arch is `rust-bat` on Debian and Fedora; `fd` on Arch is `rust-fd-find` on Debian; Nixpkgs uses specific attribute paths). `pkgmap` provides an offline SQLite database and a companion Python library/CLI to translate package names between any pair of Linux distributions, resolve packages across all repositories, or look up native packages by upstream project name.
 
-Data is updated daily from [Repology](https://repology.org) and indexed for instant local lookups. On first run, `pkgmap` automatically downloads and decompresses the latest daily database release (`~/.cache/pkgmap/pkgmap.db`).
+Data is updated daily from [Repology](https://repology.org) and indexed for instant local lookups. On first run, `pkgmap` automatically downloads and decompresses the latest daily database snapshot (`~/.cache/pkgmap/`).
+
+- **PyPI**: [`pkgmap-py`](https://pypi.org/project/pkgmap-py/)
+- **Web Interface**: [levizor.github.io/pkgmap](https://levizor.github.io/pkgmap/) (runs 100% client-side via SQLite WebAssembly + OPFS)
 
 ---
 
@@ -17,13 +20,28 @@ Use `--from` (`-f`) and `--to` (`-t`):
 ```bash
 # What is Arch's 'bat' called in Debian?
 pkgmap resolve bat --from arch --to debian
-# Output: rust-bat (0.22.1) [category: misc]
+# Output: rust-bat (0.24.0)
 
 # What is Arch's 'fd' in Nixpkgs?
 pkgmap resolve fd -f arch -t nixpkgs
 # Output: fd (10.5.0)
 ```
 
+### Batch resolution
+
+Pass multiple package names to resolve them in a single query:
+
+```bash
+pkgmap resolve git gcc bat --from nix --to gnuguix
+```
+
+Output:
+```text
+git -> git (2.54.0)
+gcc -> gcc (15.2.0)
+bat -> bat (0.26.1)
+```
+
 ### Resolve across all distributions
 
 Omit `--to` to see equivalents across every indexed distribution:
@@ -34,8 +52,8 @@ pkgmap resolve bat --from arch
 
 Output:
 ```text
-alpine_3_20: bat (0.24.0)
-debian_12: rust-bat (0.22.1) [category: misc]
+alpine_edge: bat (0.24.0)
+debian_unstable: rust-bat (0.24.0)
 fedora_rawhide: rust-bat (0.26.1)
 nix_unstable: bat (0.26.1)
 ubuntu_24_04: rust-bat (0.24.0)
@@ -48,7 +66,7 @@ Omit `--from` (or pass `--project` / `-p`) to resolve packages directly from an
 
 ```bash
 pkgmap resolve ripgrep --to debian
-# Output: rust-ripgrep (13.0.0) [category: misc]
+# Output: rust-ripgrep (14.1.0)
 ```
 
 ### JSON output
@@ -63,15 +81,15 @@ pkgmap resolve bat -f arch -t debian --json
 [
   {
     "name": "rust-bat",
-    "version": "0.22.1",
-    "category": "misc",
-    "repo": "debian_12",
-    "repo_family": "debuntu",
-    "install_name": "rust-bat"
+    "version": "0.24.0",
+    "repo": "debian_unstable",
+    "repo_family": "debuntu"
   }
 ]
 ```
 
+When multiple packages are passed with `--json`, the output is a dictionary keyed by each input package name.
+
 ### Other commands
 
 ```bash
@@ -80,27 +98,47 @@ pkgmap repos
 
 # Manually refresh the local database snapshot
 pkgmap update
+
+# Download the full database (all 330+ Repology repositories)
+pkgmap update --full
 ```
 
 ---
 
+## Core vs. Full Database Variants
+
+`pkgmap` publishes two database snapshots with every daily release:
+
+| Variant | File | Compressed Size | Coverage | Default For |
+| :--- | :--- | :--- | :--- | :--- |
+| **Core** | `pkgmap-core.db` | ~7 MB | Top 10 repositories (Nixpkgs, Arch, AUR, Debian, Ubuntu, Fedora, Alpine, openSUSE, Gentoo, Void) | **CLI & Web UI** |
+| **Full** | `pkgmap.db` | ~37 MB | All 330+ Repology repositories | **Python Library** |
+
+- **CLI behavior**: Defaults to the **Core** database (`~/.cache/pkgmap/pkgmap-core.db`) unless the Full database is already downloaded locally or `--full` is passed. If you query a repository not present in Core, the CLI prompts you to run `pkgmap update --full`. You can also pass `--core` or `--full` to any CLI command (`resolve`, `update`, `repos`).
+- **Python library behavior**: Defaults to the **Full** database (`~/.cache/pkgmap/pkgmap.db`). Call `set_default_variant("core")` (or set `PKGMAP_DB_VARIANT=core`) to use the Core database instead.
+
+---
+
 ## Python API
 
-You can also use `pkgmap` as a Python library:
+You can use `pkgmap` as a Python library:
 
 ```python
-from pkgmap import resolve, resolve_all, resolve_batch
+from pkgmap import resolve, resolve_all, resolve_batch, set_default_variant
+
+# Optional: switch library default from 'full' to 'core'
+# set_default_variant("core")
 
 # 1. Single package resolution
 res = resolve("bat", from_repo="arch", to_repo="debian")
 if res:
-    print(res.install_name, res.version)
-    # Output: rust-bat 0.22.1
+    print(res.name, res.version)
+    # Output: rust-bat 0.24.0
 
 # 2. Query all repositories for equivalents
 matches = resolve_all("bat", from_repo="arch")
 for r in matches:
-    print(f"{r.repo}: {r.install_name}")
+    print(f"{r.repo}: {r.name}")
 
 # 3. High-performance batch resolution (executed in a single SQL query)
 packages = ["bat", "fd", "ripgrep"]
@@ -108,7 +146,7 @@ results = resolve_batch(packages, from_repo="arch", to_repo="nixpkgs")
 
 for pkg, match in results.items():
     if match:
-        print(f"{pkg} -> {match.install_name}")
+        print(f"{pkg} -> {match.name}")
 ```
 
 ### API Methods
@@ -118,20 +156,24 @@ for pkg, match in results.items():
 - `resolve_batch(packages, from_repo=None, to_repo=None, db_path=None)`: Resolves a sequence of packages in a single batch query, returning `{package: PackageResolution | None}`.
 - `resolve_batch_all(packages, from_repo=None, to_repo=None, db_path=None)`: Batch resolution returning `{package: list[PackageResolution]}`.
 - `list_repositories(db_path=None)`: Returns all repositories with package counts and families.
+- `set_default_variant(variant)`: Sets the default database variant (`"full"` or `"core"`).
+- `get_default_variant()`: Returns the active default database variant.
 
 ---
 
 ## Configuration
 
-By default, the database is stored at:
-- `~/.cache/pkgmap/pkgmap.db`
+By default, databases are cached at:
+- Full database: `~/.cache/pkgmap/pkgmap.db`
+- Core database: `~/.cache/pkgmap/pkgmap-core.db`
 
-You can customize the location using:
-- The `PKGMAP_DB_PATH` environment variable:
+You can customize behavior using environment variables:
+- `PKGMAP_DB_VARIANT`: Set to `core` or `full` to override the default database variant.
+- `PKGMAP_DB_PATH`: Override the database file path directly:
   ```bash
   export PKGMAP_DB_PATH="/path/to/custom/pkgmap.db"
   ```
-- Or the `--db-path` argument on the CLI / `db_path` parameter in Python.
+- Or pass `--db-path` on the CLI / `db_path` in Python.
 
 ---
 

{pkgmap_py-0.1.0 → pkgmap_py-0.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pkgmap-py"
-version = "0.1.0"
+version = "0.2.0"
 description = "Cross-distribution Linux package name resolution"
 readme = "README.md"
 requires-python = ">=3.12"

{pkgmap_py-0.1.0 → pkgmap_py-0.2.0}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "pkgmap-py"
-version = "0.1.0"
+version = "0.2.0"
 description = "Cross-distribution Linux package name resolution"
 authors = [{ name = "Levizor", email = "levizor@disroot.org" }]
 license = { text = "MIT" }

{pkgmap_py-0.1.0 → pkgmap_py-0.2.0}/src/pkgmap/__init__.py

@@ -1,6 +1,13 @@
 """Cross-distribution Linux package name resolution library."""
 
-from pkgmap.db import ensure_database, get_database_path, update_database
+from pkgmap.db import (
+    DatabaseVariant,
+    ensure_database,
+    get_database_path,
+    get_default_variant,
+    set_default_variant,
+    update_database,
+)
 from pkgmap.resolver import (
     PackageResolution,
     list_repositories,
@@ -11,16 +18,19 @@ from pkgmap.resolver import (
     resolve_project,
 )
 
-__version__ = "0.1.0"
+__version__ = "0.2.0"
 __all__ = [
+    "DatabaseVariant",
     "PackageResolution",
     "ensure_database",
     "get_database_path",
+    "get_default_variant",
     "list_repositories",
     "resolve",
     "resolve_all",
     "resolve_batch",
     "resolve_batch_all",
     "resolve_project",
+    "set_default_variant",
     "update_database",
 ]

{pkgmap_py-0.1.0 → pkgmap_py-0.2.0}/src/pkgmap/apps.py

@@ -53,6 +53,21 @@ def pipeline_build(
             help="Path for the output SQLite database",
         ),
     ] = Path("pkgmap.db"),
+    core_output_file: Annotated[
+        Path | None,
+        typer.Option(
+            "-c",
+            "--core-output-path",
+            help="Optional path for the core subset SQLite database (e.g. pkgmap-core.db)",
+        ),
+    ] = None,
+    repos_config: Annotated[
+        Path | None,
+        typer.Option(
+            "--repos-config",
+            help="Optional path to repos.toml configuration file",
+        ),
+    ] = None,
     batch_size: Annotated[
         int,
         typer.Option(
@@ -73,6 +88,8 @@ def pipeline_build(
     pipeline.main(
         dump_file=input_dump,
         output_file=output_file,
+        core_output_file=core_output_file,
+        repos_config=repos_config,
         batch_size=batch_size,
         release_notes=release_notes,
         dump_date=dump_date,