feat: merged German diagnostics

.gitignore

@@ -6,6 +6,12 @@ build
 *.pdf
 node_modules
 mariadb_data
+pr-drafts/
 
 # Ignore direnv files
 .direnv/*
+
+# Ignore local documentation files
+.local-docs/
+harper-core/german_dictionary.dict
+docs/

.harper-dictionary.txt

@@ -0,0 +1,3 @@
+
+SvelteKit
+harper

AGENTS.md

@@ -1,6 +1,6 @@
 # Harper Docs Map for Agents
 
-This repository’s documentation site is powered by Vite + SvelteKit + SveltePress.
+this repository’s documentation site is powered by Vite + SvelteKit + SveltePress.
 
 Use `packages/web/vite.config.ts` as the source of truth for documentation scope:
 - Sidebar and important doc routes are defined in `packages/web/vite.config.ts`.
@@ -45,7 +45,7 @@ Agents should remind humans of this when possible.
 - `packages/web/src/routes/docs/weir/+page.md`: Weir rule language reference with syntax, expression types, and examples. Very important if you're asked to write a Weir rule.
 - `packages/web/src/routes/docs/rules/+page.svelte`: Live/generated rule catalog (rule names, defaults, and descriptions).
 - `packages/web/src/routes/docs/integrations/obsidian/+page.md`: Obsidian plugin overview, privacy/value comparison, installation, and support links.
-- `packages/web/src/routes/docs/integrations/chrome-extension/+page.md`: End-user Chrome extension overview and install link.
+- `packages/web/src/routes/docs/integrations/chrome-extension/+page.md`: End-user Chrome Extension overview and install link.
 - `packages/web/src/routes/docs/integrations/firefox-extension/+page.md`: End-user Firefox extension overview and install link.
 - `packages/web/src/routes/docs/integrations/wordpress/+page.md`: Current WordPress guidance, including migration recommendation to Chrome extension and legacy plugin status.
 - `packages/web/src/routes/docs/integrations/language-server/+page.md`: `harper-ls` install methods, dictionaries, code actions, ignore comments, and full configuration reference.
@@ -82,7 +82,7 @@ Agents should remind humans of this when possible.
 - `packages/web/src/routes/docs/about/+page.ts`: Route behavior helper (`ssr = false`) for the About page.
 - `packages/web/src/routes/docs/harperjs/CDN/example/+server.ts`: Serves the HTML example used by the `harper.js` CDN documentation page.
 
-## External Sidebar Targets (No Local Source File)
+## External Sidebar Targets (no Local Source File)
 
 - `https://docs.rs/harper-core/latest/harper_core/`
 - `/docs/harperjs/ref/index.html` (generated API reference target)

harper-cli/src/input/single_input.rs

@@ -142,7 +142,7 @@ impl SingleInputTrait for FileInput {
             Some("lhs") => Box::new(LiterateHaskellParser::new_markdown(
                 MarkdownOptions::default(),
             )),
-            Some("org") => Box::new(OrgMode),
+            Some("org") => Box::new(OrgMode::default()),
             Some("tex" | "latex" | "sty" | "cls" | "dtx") => Box::new(harper_tex::TeX::default()),
             Some("typ") => Box::new(harper_typst::Typst),
             Some("py") | Some("pyi") => Box::new(PythonParser::default()),

harper-cli/src/main.rs

@@ -1,12 +1,14 @@
 #![doc = include_str!("../README.md")]
 
-use harper_core::spell::{Dictionary, FstDictionary, MutableDictionary, WordId};
+use harper_core::spell::{
+    Dictionary, FstDictionary, MutableDictionary, WordId, curated_german_dictionary,
+};
 use hashbrown::HashMap;
 use std::collections::BTreeMap;
 use std::fs::File;
 use std::io::{self, BufReader};
 use std::path::PathBuf;
-// use std::sync::Arc;
+use std::sync::Arc;
 use std::{fs, process};
 
 use anyhow::anyhow;
@@ -255,9 +257,15 @@ fn main() -> anyhow::Result<()> {
             let dialect = parse_dialect(&dialect_str)
                 .map_err(|e| anyhow!("Invalid dialect '{}': {}", dialect_str, e))?;
 
+            let dict: Arc<dyn Dictionary> = if dialect.is_german() {
+                curated_german_dictionary()
+            } else {
+                curated_dictionary.clone()
+            };
+
             lint(
                 markdown_options,
-                curated_dictionary,
+                dict,
                 inputs,
                 LintOptions {
                     count,
@@ -1008,6 +1016,9 @@ fn parse_dialect(dialect: &str) -> anyhow::Result<Dialect> {
         "au" | "aus" | "australia" | "australian" | "en-au" | "en_au" => Ok(Dialect::Australian),
         "in" | "india" | "indian" | "bharat" | "en-in" | "en_in" => Ok(Dialect::Indian),
         "ca" | "canada" | "canadian" | "en-ca" | "en_ca" => Ok(Dialect::Canadian),
+        "de" | "german" | "deutsch" | "de-de" | "de_de" => Ok(Dialect::German),
+        "at" | "austria" | "austrian" | "de-at" | "de_at" => Ok(Dialect::GermanAustrian),
+        "ch" | "switzerland" | "swiss" | "de-ch" | "de_ch" => Ok(Dialect::GermanSwiss),
         _ => Err(anyhow!("Unknown dialect: {}", dialect)),
     }
 }

harper-core/Cargo.toml

@@ -36,6 +36,7 @@ bitflags = { version = "2.11.0", features = ["serde"] }
 trie-rs = "0.4.2"
 zip = { version = "8.6.0", default-features = false, features = ["deflate"] }
 regex = "1.12.3"
+flate2 = "1.1"
 
 [dev-dependencies]
 criterion = { version = "0.8.2", default-features = false }

harper-core/build.rs

@@ -1,44 +1,96 @@
-use std::{env, fs, path::PathBuf};
-
-fn main() {
-    let manifest_dir = PathBuf::from(env::var("CARGO_MANIFEST_DIR").unwrap());
-    let weir_rule_dir = manifest_dir.join("./src/linting/weir_rules");
-    let out_dir = PathBuf::from(env::var("OUT_DIR").unwrap());
-    let dest = out_dir.join("weir_rules_generated_list.rs");
+//! Build script for Harper core library.
+//!
+//! This script generates test boilerplate for Weir rules (pattern-based linters).
+//! Weir rules are defined in `.weir` files with inline tests, and this script
+//! automatically generates Rust test functions at compile time.
+//!
+//! ## German Language Support
+//!
+//! For German language support, we maintain a separate directory of Weir rules
+//! at `src/linting/weir_rules/de/`. Each rule defines common German error patterns
+//! (e.g., "bei beim" → "beim", "viele Dank" → "vielen Dank").
+//!
+//! The build script:
+//! 1. Scans both English and German Weir rule directories
+//! 2. Generates two separate test lists: `weir_rules_generated_list.rs` and
+//!    `german_weir_rules_generated_list.rs`
+//! 3. Sets environment variables so the code can locate the rules at runtime
+//!
+//! ## Adding New Weir Rules
+//!
+//! To add a new German Weir rule:
+//! 1. Create a new `.weir` file in `src/linting/weir_rules/de/`
+//! 2. Define the pattern, message, and inline tests
+//! 3. Rebuild - the build script will automatically include it in the generated list
 
-    let mut files: Vec<PathBuf> = fs::read_dir(&weir_rule_dir)
-        .unwrap()
-        .filter_map(Result::ok)
-        .filter(|e| e.file_type().unwrap().is_file())
-        .map(|e| e.path().to_path_buf())
-        .collect();
+use std::{env, fs, path::PathBuf};
 
-    files.sort();
+/// Collect all `.weir` files from a directory, sorted alphabetically.
+/// Returns an empty vector if the directory doesn't exist (for optional language support).
+fn collect_weir_files(dir: &PathBuf) -> Vec<PathBuf> {
+    match fs::read_dir(dir) {
+        Ok(entries) => {
+            let mut files: Vec<PathBuf> = entries
+                .filter_map(Result::ok)
+                .filter(|e| e.file_type().unwrap().is_file())
+                .map(|e| e.path())
+                .filter(|p| p.extension().map(|e| e == "weir").unwrap_or(false))
+                .collect();
+            files.sort();
+            files
+        }
+        Err(_) => vec![],
+    }
+}
 
+/// Generate Rust code that creates test functions for each Weir rule.
+/// The output is a file containing: `generate_boilerplate!{[Rule1, Rule2, ...]}`
+/// which is then expanded by the macro in `src/linting/weir_rules/mod.rs`.
+fn write_boilerplate(files: &[PathBuf], dest: &PathBuf) {
     let mut code = String::new();
-
     code.push_str("generate_boilerplate!{[");
-
     for file in files {
-        if file
-            .file_name()
-            .unwrap()
-            .to_string_lossy()
-            .ends_with(".weir")
-        {
-            code.push_str(&format!(
-                "{},\n",
-                file.file_stem().unwrap().to_str().unwrap()
-            ));
-        }
+        code.push_str(&format!(
+            "{},\n",
+            file.file_stem().unwrap().to_str().unwrap()
+        ));
     }
-
     code.push_str("]}");
+    fs::write(dest, code).unwrap();
+}
+
+fn main() {
+    // Locate source directories for Weir rules
+    let manifest_dir = PathBuf::from(env::var("CARGO_MANIFEST_DIR").unwrap());
+    let weir_rule_dir = manifest_dir.join("./src/linting/weir_rules");
+    let german_weir_rule_dir = manifest_dir.join("./src/linting/weir_rules/de");
+    let out_dir = PathBuf::from(env::var("OUT_DIR").unwrap());
+
+    // Generate test lists for both English and German Weir rules
+    let dest = out_dir.join("weir_rules_generated_list.rs");
+    let de_dest = out_dir.join("german_weir_rules_generated_list.rs");
+
+    let files = collect_weir_files(&weir_rule_dir);
+    write_boilerplate(&files, &dest);
 
-    fs::write(&dest, code).unwrap();
+    let de_files = collect_weir_files(&german_weir_rule_dir);
+    write_boilerplate(&de_files, &de_dest);
 
+    // Tell Cargo to rerun this script if any Weir files change
     println!("cargo:rerun-if-changed={}", weir_rule_dir.display());
+    println!("cargo:rerun-if-changed={}", german_weir_rule_dir.display());
     println!("cargo:rerun-if-changed=build.rs");
+
+    // Export environment variables for use in the codebase
+    // These allow the code to locate Weir rule files and generated test lists at runtime
     println!("cargo:rustc-env=WEIR_RULE_DIR={}", weir_rule_dir.display());
+    println!(
+        "cargo:rustc-env=GERMAN_WEIR_RULE_DIR={}",
+        german_weir_rule_dir.display()
+    );
     println!("cargo:rustc-env=WEIR_RULE_LIST={}", dest.display());
+    println!(
+        "cargo:rustc-env=GERMAN_WEIR_RULE_LIST={}",
+        de_dest.display()
+    );
 }