forgery 0.2.0__tar.gz → 0.3.0__tar.gz

{forgery-0.2.0 → forgery-0.3.0}/CHANGELOG.md

@@ -7,8 +7,26 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.3.0] - 2026-03-17
+
 ### Added
 
+- **Web & HTML Providers**: Full suite of web content generators
+  - `url_path()` / `url_paths(n)`: URL paths (e.g., "/blog/products/42")
+  - `url_slug()` / `url_slugs(n)`: URL slugs (e.g., "ultimate-guide-2024")
+  - `query_string()` / `query_strings(n)`: Query strings (e.g., "?page=2&sort=date")
+  - `meta_description()` / `meta_descriptions(n)`: HTML meta description tags
+  - `og_tags()` / `og_tags_batch(n)`: Open Graph meta tag sets
+  - `hreflang_tags()` / `hreflang_tags_batch(n)`: Hreflang link tags with x-default
+  - `img_tag(ratio)` / `img_tags(n, ratio)`: Image tags with configurable missing-alt ratio
+  - `http_headers()` / `http_headers_batch(n)`: HTTP response header dicts
+  - `content_type_header()` / `content_type_headers(n)`: Content-Type values
+  - `robots_txt()` / `robots_txts(n)`: robots.txt file contents
+  - `html_page(**kwargs)` / `html_pages(n, **kwargs)`: Full HTML5 pages with 9 configurable parameters
+  - `website(pages, domain)`: Interlinked website as dict of URL to HTML with spanning-tree connectivity
+- **Schema integration**: `url_path`, `url_slug`, `query_string` work in `records()` / `records_arrow()`
+- **Criterion benchmarks** for url_paths, html_page, and website generators
+
 - **Custom Providers API** (Phase 3.2): Register your own data providers
   - `add_provider(name, options)`: Register uniform (equal probability) provider
   - `add_weighted_provider(name, weighted_options)`: Register weighted provider
@@ -130,5 +148,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - SonarCloud integration for code quality
 - CodeQL static analysis
 
-[Unreleased]: https://github.com/williajm/forgery/compare/v0.1.0...HEAD
+[Unreleased]: https://github.com/williajm/forgery/compare/v0.3.0...HEAD
+[0.3.0]: https://github.com/williajm/forgery/compare/v0.2.0...v0.3.0
 [0.1.0]: https://github.com/williajm/forgery/releases/tag/v0.1.0

{forgery-0.2.0 → forgery-0.3.0}/Cargo.lock

@@ -452,7 +452,7 @@ checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
 [[package]]
 name = "forgery"
-version = "0.2.0"
+version = "0.3.0"
 dependencies = [
  "arrow-array",
  "arrow-buffer",

{forgery-0.2.0 → forgery-0.3.0}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "forgery"
-version = "0.2.0"
+version = "0.3.0"
 edition = "2021"
 description = "Fake data at the speed of Rust"
 license = "MIT"

{forgery-0.2.0 → forgery-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: forgery
-Version: 0.2.0
+Version: 0.3.0
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -231,6 +231,44 @@ fake2.emails(100)
 | `ipv6s(n)` | `ipv6()` | IPv6 addresses |
 | `mac_addresses(n)` | `mac_address()` | MAC addresses |
 
+### Web & HTML
+
+| Batch | Single | Description |
+|-------|--------|-------------|
+| `url_paths(n)` | `url_path()` | URL paths (e.g., "/blog/products/42") |
+| `url_slugs(n)` | `url_slug()` | URL slugs (e.g., "ultimate-guide-2024") |
+| `query_strings(n)` | `query_string()` | Query strings (e.g., "?page=2&sort=date") |
+| `meta_descriptions(n)` | `meta_description()` | HTML meta description tags |
+| `og_tags_batch(n)` | `og_tags()` | Open Graph meta tag sets (multi-line) |
+| `hreflang_tags_batch(n)` | `hreflang_tags()` | Hreflang link tag sets with x-default |
+| `img_tags(n, ratio)` | `img_tag(ratio)` | Image tags (configurable missing alt ratio) |
+| `content_type_headers(n)` | `content_type_header()` | Content-Type header values |
+| `http_headers_batch(n)` | `http_headers()` | HTTP response header dicts |
+| `robots_txts(n)` | `robots_txt()` | robots.txt file contents |
+| `html_pages(n, ...)` | `html_page(...)` | Full HTML5 pages with configurable SEO elements |
+| - | `website(pages, domain)` | Interlinked website (dict of URL → HTML) |
+
+```python
+from forgery import Faker
+
+fake = Faker()
+fake.seed(42)
+
+# Generate a full HTML page with SEO elements
+page = fake.html_page(
+    headings=4,
+    internal_links=5,
+    images=3,
+    include_og_tags=True,
+    domain="mysite.com",
+)
+
+# Generate an interlinked website for crawl testing
+site = fake.website(pages=20, domain="example.com")
+# site = {"https://example.com/": "<html>...", "https://example.com/blog/guide": "<html>...", ...}
+# Every page is reachable from the homepage via link traversal
+```
+
 ### Finance
 
 | Batch | Single | Description |
@@ -571,7 +609,7 @@ pandas, DuckDB, etc.).
 | Date range | `("date", start, end)` | `("date", "2020-01-01", "2024-12-31")` |
 | Choice | `("choice", [options])` | `("choice", ["a", "b", "c"])` |
 
-All simple types from the generators above are supported: `name`, `first_name`, `last_name`, `email`, `safe_email`, `free_email`, `phone`, `uuid`, `int`, `float`, `date`, `datetime`, `street_address`, `city`, `state`, `country`, `zip_code`, `address`, `company`, `job`, `catch_phrase`, `url`, `domain_name`, `ipv4`, `ipv6`, `mac_address`, `credit_card`, `iban`, `sentence`, `paragraph`, `text`, `color`, `hex_color`, `rgb_color`, `md5`, `sha256`, `latitude`, `longitude`, `coordinate`, `boolean`, `ssn`, `file_name`, `file_extension`, `mime_type`, `file_path`, `license_plate`, `vehicle_make`, `vehicle_model`, `vehicle_year`, `vin`, `ean13`, `ean8`, `upc_a`, `upc_e`, `isbn10`, `isbn13`, `product_name`, `product_category`, `department`, `product_material`.
+All simple types from the generators above are supported: `name`, `first_name`, `last_name`, `email`, `safe_email`, `free_email`, `phone`, `uuid`, `int`, `float`, `date`, `datetime`, `street_address`, `city`, `state`, `country`, `zip_code`, `address`, `company`, `job`, `catch_phrase`, `url`, `domain_name`, `ipv4`, `ipv6`, `mac_address`, `credit_card`, `iban`, `sentence`, `paragraph`, `text`, `color`, `hex_color`, `rgb_color`, `md5`, `sha256`, `latitude`, `longitude`, `coordinate`, `boolean`, `ssn`, `file_name`, `file_extension`, `mime_type`, `file_path`, `license_plate`, `vehicle_make`, `vehicle_model`, `vehicle_year`, `vin`, `ean13`, `ean8`, `upc_a`, `upc_e`, `isbn10`, `isbn13`, `product_name`, `product_category`, `department`, `product_material`, `url_path`, `url_slug`, `query_string`.
 
 ## Async Generation
 

{forgery-0.2.0 → forgery-0.3.0}/README.md

@@ -197,6 +197,44 @@ fake2.emails(100)
 | `ipv6s(n)` | `ipv6()` | IPv6 addresses |
 | `mac_addresses(n)` | `mac_address()` | MAC addresses |
 
+### Web & HTML
+
+| Batch | Single | Description |
+|-------|--------|-------------|
+| `url_paths(n)` | `url_path()` | URL paths (e.g., "/blog/products/42") |
+| `url_slugs(n)` | `url_slug()` | URL slugs (e.g., "ultimate-guide-2024") |
+| `query_strings(n)` | `query_string()` | Query strings (e.g., "?page=2&sort=date") |
+| `meta_descriptions(n)` | `meta_description()` | HTML meta description tags |
+| `og_tags_batch(n)` | `og_tags()` | Open Graph meta tag sets (multi-line) |
+| `hreflang_tags_batch(n)` | `hreflang_tags()` | Hreflang link tag sets with x-default |
+| `img_tags(n, ratio)` | `img_tag(ratio)` | Image tags (configurable missing alt ratio) |
+| `content_type_headers(n)` | `content_type_header()` | Content-Type header values |
+| `http_headers_batch(n)` | `http_headers()` | HTTP response header dicts |
+| `robots_txts(n)` | `robots_txt()` | robots.txt file contents |
+| `html_pages(n, ...)` | `html_page(...)` | Full HTML5 pages with configurable SEO elements |
+| - | `website(pages, domain)` | Interlinked website (dict of URL → HTML) |
+
+```python
+from forgery import Faker
+
+fake = Faker()
+fake.seed(42)
+
+# Generate a full HTML page with SEO elements
+page = fake.html_page(
+    headings=4,
+    internal_links=5,
+    images=3,
+    include_og_tags=True,
+    domain="mysite.com",
+)
+
+# Generate an interlinked website for crawl testing
+site = fake.website(pages=20, domain="example.com")
+# site = {"https://example.com/": "<html>...", "https://example.com/blog/guide": "<html>...", ...}
+# Every page is reachable from the homepage via link traversal
+```
+
 ### Finance
 
 | Batch | Single | Description |
@@ -537,7 +575,7 @@ pandas, DuckDB, etc.).
 | Date range | `("date", start, end)` | `("date", "2020-01-01", "2024-12-31")` |
 | Choice | `("choice", [options])` | `("choice", ["a", "b", "c"])` |
 
-All simple types from the generators above are supported: `name`, `first_name`, `last_name`, `email`, `safe_email`, `free_email`, `phone`, `uuid`, `int`, `float`, `date`, `datetime`, `street_address`, `city`, `state`, `country`, `zip_code`, `address`, `company`, `job`, `catch_phrase`, `url`, `domain_name`, `ipv4`, `ipv6`, `mac_address`, `credit_card`, `iban`, `sentence`, `paragraph`, `text`, `color`, `hex_color`, `rgb_color`, `md5`, `sha256`, `latitude`, `longitude`, `coordinate`, `boolean`, `ssn`, `file_name`, `file_extension`, `mime_type`, `file_path`, `license_plate`, `vehicle_make`, `vehicle_model`, `vehicle_year`, `vin`, `ean13`, `ean8`, `upc_a`, `upc_e`, `isbn10`, `isbn13`, `product_name`, `product_category`, `department`, `product_material`.
+All simple types from the generators above are supported: `name`, `first_name`, `last_name`, `email`, `safe_email`, `free_email`, `phone`, `uuid`, `int`, `float`, `date`, `datetime`, `street_address`, `city`, `state`, `country`, `zip_code`, `address`, `company`, `job`, `catch_phrase`, `url`, `domain_name`, `ipv4`, `ipv6`, `mac_address`, `credit_card`, `iban`, `sentence`, `paragraph`, `text`, `color`, `hex_color`, `rgb_color`, `md5`, `sha256`, `latitude`, `longitude`, `coordinate`, `boolean`, `ssn`, `file_name`, `file_extension`, `mime_type`, `file_path`, `license_plate`, `vehicle_make`, `vehicle_model`, `vehicle_year`, `vin`, `ean13`, `ean8`, `upc_a`, `upc_e`, `isbn10`, `isbn13`, `product_name`, `product_category`, `department`, `product_material`, `url_path`, `url_slug`, `query_string`.
 
 ## Async Generation
 

{forgery-0.2.0 → forgery-0.3.0}/benches/generators.rs

@@ -204,6 +204,76 @@ fn bench_records_generation(c: &mut Criterion) {
     group.finish();
 }
 
+fn bench_url_paths(c: &mut Criterion) {
+    let mut group = c.benchmark_group("url_paths");
+
+    for size in [100, 1_000, 10_000].iter() {
+        group.throughput(Throughput::Elements(*size as u64));
+        group.bench_with_input(
+            criterion::BenchmarkId::from_parameter(size),
+            size,
+            |b, &size| {
+                let mut faker = Faker::new("en_US").unwrap();
+                faker.seed(42);
+                b.iter(|| {
+                    let paths = faker.url_paths(black_box(size)).unwrap();
+                    black_box(paths)
+                });
+            },
+        );
+    }
+    group.finish();
+}
+
+fn bench_html_page(c: &mut Criterion) {
+    let mut group = c.benchmark_group("html_page");
+
+    group.bench_function("single", |b| {
+        let mut faker = Faker::new("en_US").unwrap();
+        faker.seed(42);
+        let opts = _forgery::providers::html::HtmlPageOptions::default();
+        b.iter(|| black_box(faker.html_page(&opts)));
+    });
+
+    for size in [10, 100, 1_000].iter() {
+        group.throughput(Throughput::Elements(*size as u64));
+        group.bench_with_input(
+            criterion::BenchmarkId::new("batch", size),
+            size,
+            |b, &size| {
+                let mut faker = Faker::new("en_US").unwrap();
+                faker.seed(42);
+                let opts = _forgery::providers::html::HtmlPageOptions::default();
+                b.iter(|| {
+                    let pages = faker.html_pages(black_box(size), &opts).unwrap();
+                    black_box(pages)
+                });
+            },
+        );
+    }
+    group.finish();
+}
+
+fn bench_website(c: &mut Criterion) {
+    let mut group = c.benchmark_group("website");
+
+    for size in [5, 20, 100].iter() {
+        group.bench_with_input(
+            criterion::BenchmarkId::from_parameter(size),
+            size,
+            |b, &size| {
+                let mut faker = Faker::new("en_US").unwrap();
+                faker.seed(42);
+                b.iter(|| {
+                    let site = faker.website(black_box(size), "example.com").unwrap();
+                    black_box(site)
+                });
+            },
+        );
+    }
+    group.finish();
+}
+
 criterion_group!(
     benches,
     bench_name_generation,
@@ -211,6 +281,9 @@ criterion_group!(
     bench_uuid_generation,
     bench_integer_generation,
     bench_single_value_generation,
-    bench_records_generation
+    bench_records_generation,
+    bench_url_paths,
+    bench_html_page,
+    bench_website,
 );
 criterion_main!(benches);

{forgery-0.2.0 → forgery-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "forgery"
-version = "0.2.0"
+version = "0.3.0"
 description = "Fake data at the speed of Rust"
 readme = "README.md"
 license = { text = "MIT" }