tweaks

.gitignore

@@ -1,4 +1,3 @@
 .env
-BLOGPOST.md
-TRANSLATED_BLOGPOST.md
-SOURCE.md
+output/*.md
+output/*.txt

INSTRUCTIONS.md

@@ -1 +1,32 @@
-Írj egy kedves, pozitív hangvételű blogpost-ot ami tájékoztat arról, hogy épp min dolgozunk.
+# Task
+
+- Write a public-facing blog post on behalf of a development team.
+- Rely strictly on internal meeting notes.
+- Do not add any outside information or unverified claims.
+
+# Style
+
+- Warm and enthusiastic tone.
+- Concise, filler-free phrasing.
+- Meaningful information in every sentence.
+- Target audience is technical; use industry jargon.
+- Do not explain basic concepts.
+
+# Content
+
+- Address every point in the source material.
+- Guessing or speculating is strictly prohibited.
+- If information is missing or unclear, do not invent details.
+- Professional pride, not a marketing pitch or press release.
+- Short, punchy opening to set the context.
+- Body: completed work, progress, decisions, and challenges.
+- Closing: future steps based only on the source material.
+
+# Formatting
+
+- Use Markdown.
+- Single `#` for the title (specific and technical).
+- Use `##` for subheadings.
+- Short paragraphs (3-5 sentences each).
+- No bullet points or lists in the body text; write in flowing prose.
+- Total length: 300-500 words.

Makefile

@@ -1,23 +1,27 @@
 ENV = export $(shell cat .env | grep -v '^\#' | grep -v '^$$' | xargs)
 
-.PHONY: fetch write translate upload all
+.PHONY: fetch write translate upload clean all
 
-## Letölt egy wiki oldalt SOURCE.md-be
-## Használat: make fetch URL=/path/to/page
+## Downloads a wiki page into SOURCE.md
+## Usage: make fetch URL=/path/to/page
 fetch:
-	$(ENV) && python3 generator.py fetch $(URL)
+	@$(ENV) && python3 generator.py fetch $(URL)
 
-## Blogposztot ír SOURCE.md-ből → BLOGPOST.md
+## Writes a blog post from SOURCE.md → BLOGPOST.md
 write:
-	$(ENV) && python3 generator.py write
+	@$(ENV) && python3 generator.py write
 
-## Lefordítja BLOGPOST.md → TRANSLATED_BLOGPOST.md
+## Translates BLOGPOST.md → TRANSLATED_BLOGPOST.md
 translate:
-	$(ENV) && python3 generator.py translate
+	@$(ENV) && python3 generator.py translate
 
-## Feltölti TRANSLATED_BLOGPOST.md-t a wikire
+## Uploads TRANSLATED_BLOGPOST.md to the wiki
 upload:
-	$(ENV) && python3 generator.py upload
+	@$(ENV) && python3 generator.py upload
 
-## Teljes pipeline: write → translate → upload
+## Deletes .md files from the output directory
+clean:
+	@$(ENV) && python3 generator.py clean
+
+## Full pipeline: write → translate → upload
 all: write translate upload

generator.py

@@ -25,17 +25,94 @@ import urllib.request
 import urllib.error
 
 # ---------------------------------------------------------------------------
-# Config
+# Config & Templates
 # ---------------------------------------------------------------------------
 
-SOURCE_FILE      = "SOURCE.md"
-BLOGPOST_FILE    = "BLOGPOST.md"
-TRANSLATED_FILE  = "TRANSLATED_BLOGPOST.md"
+OUTPUT_DIR        = "output"
+SOURCE_FILE       = os.path.join(OUTPUT_DIR, "SOURCE.md")
+SOURCE_TITLE_FILE = os.path.join(OUTPUT_DIR, "SOURCE_TITLE.txt")
+BLOGPOST_FILE     = os.path.join(OUTPUT_DIR, "BLOGPOST.md")
+TRANSLATED_FILE   = os.path.join(OUTPUT_DIR, "TRANSLATED_BLOGPOST.md")
 INSTRUCTIONS_FILE = "INSTRUCTIONS.md"
 
-GEMINI_MODEL     = "gemini-flash-latest"
-GEMINI_BASE_URL  = "https://generativelanguage.googleapis.com/v1beta/models"
+GEMINI_MODEL      = "gemini-flash-latest"
+GEMINI_BASE_URL   = "https://generativelanguage.googleapis.com/v1beta/models"
 
+WRITE_PROMPT_TEMPLATE = """Please read the following instructions carefully and follow them to write a blog post.
+
+## INSTRUCTIONS
+
+{instructions}
+
+## TASK
+
+Read the source content below and write a blog post from it in {original_lang} language. Output only the blog post in Markdown format, with no additional commentary.
+
+## SOURCE CONTENT
+
+{source}"""
+
+TRANSLATE_PROMPT_TEMPLATE = """Translate the following Markdown blog post into {translate_lang}. Preserve all Markdown formatting, headings, links, and code blocks exactly. Output only the translated Markdown with no additional commentary.
+
+{blogpost}"""
+
+# ---------------------------------------------------------------------------
+# GraphQL Queries
+# ---------------------------------------------------------------------------
+
+QUERY_GET_PAGE = """
+query ($path: String!) {
+  pages {
+    singleByPath(path: $path, locale: "en") {
+      id
+      title
+      description
+      content
+    }
+  }
+}
+"""
+
+QUERY_FIND_PAGE = """
+query ($path: String!) {
+  pages {
+    singleByPath(path: $path, locale: "en") {
+      id
+    }
+  }
+}
+"""
+
+MUTATION_UPDATE_PAGE = """
+mutation ($id: Int!, $content: String!, $description: String!) {
+  pages {
+    update(id: $id, content: $content, description: $description, tags: ["blog"]) {
+      responseResult { succeeded message }
+    }
+  }
+}
+"""
+
+MUTATION_CREATE_PAGE = """
+mutation ($path: String!, $title: String!, $content: String!, $description: String!) {
+  pages {
+    create(
+      path: $path
+      title: $title
+      content: $content
+      editor: "markdown"
+      locale: "en"
+      isPublished: true
+      isPrivate: false
+      tags: ["blog"]
+      description: $description
+    ) {
+      responseResult { succeeded message }
+      page { id }
+    }
+  }
+}
+"""
 
 # ---------------------------------------------------------------------------
 # Helpers
@@ -64,30 +141,6 @@ def http_post(url: str, payload: dict, headers: dict) -> dict:
         sys.exit(1)
 
 
-def wiki_graphql(base: str, token: str, query: str, variables: dict = None) -> dict:
-    url = f"{base}/graphql"
-    payload = {"query": query}
-    if variables:
-        payload["variables"] = variables
-    headers = {
-        "Authorization": f"Bearer {token}",
-        "Content-Type": "application/json",
-    }
-    return http_post(url, payload, headers)
-
-
-def gemini_generate(api_key: str, prompt: str) -> str:
-    url = f"{GEMINI_BASE_URL}/{GEMINI_MODEL}:generateContent"
-    payload = {"contents": [{"parts": [{"text": prompt}]}]}
-    headers = {"Content-Type": "application/json", "X-goog-api-key": api_key}
-    resp = http_post(url, payload, headers)
-    try:
-        return resp["candidates"][0]["content"]["parts"][0]["text"]
-    except (KeyError, IndexError) as e:
-        print(f"ERROR: Unexpected Gemini response structure: {resp}", file=sys.stderr)
-        sys.exit(1)
-
-
 def to_kebab(text: str) -> str:
     text = text.lower()
     text = re.sub(r"[^a-z0-9\s-]", "", text)
@@ -104,179 +157,177 @@ def read_file(path: str) -> str:
 
 
 def write_file(path: str, content: str) -> None:
+    os.makedirs(os.path.dirname(path), exist_ok=True)
     with open(path, "w", encoding="utf-8") as f:
         f.write(content)
     print(f"✓ Saved to {path}")
 
 
 # ---------------------------------------------------------------------------
-# Commands
+# Classes
 # ---------------------------------------------------------------------------
 
-def cmd_fetch(args):
-    """Download a Wiki.js page as Markdown via GraphQL."""
-    base  = require_env("WIKI_BASE_DOMAIN")
-    token = require_env("WIKI_TOKEN")
+class WikiJS:
+    def __init__(self, base_domain: str, token: str):
+        self.base_domain = base_domain.rstrip("/")
+        self.token = token
+        self.api_url = f"{self.base_domain}/graphql"
 
-    # Strip base domain from URL if full URL was given, then strip leading slash
-    page_path = args.url.replace(base, "").lstrip("/")
-    print(f"→ Fetching wiki page: /{page_path}")
-
-    query = """
-    query ($path: String!) {
-      pages {
-        singleByPath(path: $path, locale: "en") {
-          id
-          title
-          description
-          content
+    def graphql(self, query: str, variables: dict = None) -> dict:
+        payload = {"query": query}
+        if variables:
+            payload["variables"] = variables
+        headers = {
+            "Authorization": f"Bearer {self.token}",
+            "Content-Type": "application/json",
         }
-      }
-    }
-    """
+        return http_post(self.api_url, payload, headers)
 
-    resp = wiki_graphql(base, token, query, {"path": page_path})
-    page = resp.get("data", {}).get("pages", {}).get("singleByPath")
+    def get_page(self, path: str):
+        resp = self.graphql(QUERY_GET_PAGE, {"path": path})
+        return resp.get("data", {}).get("pages", {}).get("singleByPath"), resp
 
-    if not page:
-        errors = resp.get("errors", resp)
-        print(f"ERROR: Page not found at '{page_path}': {errors}", file=sys.stderr)
-        sys.exit(1)
+    def find_page_id(self, path: str):
+        resp = self.graphql(QUERY_FIND_PAGE, {"path": path})
+        page = resp.get("data", {}).get("pages", {}).get("singleByPath")
+        return page.get("id") if page else None
 
-    write_file(SOURCE_FILE, page["content"])
+    def update_page(self, page_id: int, content: str, description: str):
+        variables = {"id": page_id, "content": content, "description": description}
+        resp = self.graphql(MUTATION_UPDATE_PAGE, variables)
+        return resp.get("data", {}).get("pages", {}).get("update", {}).get("responseResult", {}), resp
+
+    def create_page(self, path: str, title: str, content: str, description: str):
+        variables = {"path": path, "title": title, "content": content, "description": description}
+        resp = self.graphql(MUTATION_CREATE_PAGE, variables)
+        return resp.get("data", {}).get("pages", {}).get("create", {}).get("responseResult", {}), resp
 
 
-def cmd_write(args):
-    """Generate a blog post from SOURCE.md using Gemini."""
-    api_key       = require_env("GEMINI_API_KEY")
-    original_lang = require_env("ORIGINAL_LANG", "Hungarian")
+class GoogleGemini:
+    def __init__(self, api_key: str, model: str = GEMINI_MODEL):
+        self.api_key = api_key
+        self.model = model
+        self.url = f"{GEMINI_BASE_URL}/{self.model}:generateContent"
 
-    instructions = read_file(INSTRUCTIONS_FILE)
-    source       = read_file(SOURCE_FILE)
-
-    print(f"→ Generating blog post in {original_lang} with Gemini...")
-
-    prompt = (
-        "Please read the following instructions carefully and follow them to write a blog post.\n\n"
-        "## INSTRUCTIONS\n\n"
-        f"{instructions}\n\n"
-        "## TASK\n\n"
-        f"Read the source content below and write a blog post from it in {original_lang} language. "
-        "Output only the blog post in Markdown format, with no additional commentary.\n\n"
-        "## SOURCE CONTENT\n\n"
-        f"{source}"
-    )
-
-    result = gemini_generate(api_key, prompt)
-    write_file(BLOGPOST_FILE, result)
+    def generate(self, prompt: str) -> str:
+        payload = {"contents": [{"parts": [{"text": prompt}]}]}
+        headers = {"Content-Type": "application/json", "X-goog-api-key": self.api_key}
+        resp = http_post(self.url, payload, headers)
+        try:
+            return resp["candidates"][0]["content"]["parts"][0]["text"]
+        except (KeyError, IndexError):
+            print(f"ERROR: Unexpected Gemini response structure: {resp}", file=sys.stderr)
+            sys.exit(1)
 
 
-def cmd_translate(args):
-    """Translate BLOGPOST.md to TRANSLATED_BLOGPOST.md using Gemini."""
-    api_key        = require_env("GEMINI_API_KEY")
-    translate_lang = require_env("TRANSLATE_LANG", "English")
+class BlogWriter:
+    def __init__(self):
+        self.wiki = WikiJS(
+            require_env("WIKI_BASE_DOMAIN"),
+            require_env("WIKI_TOKEN")
+        )
+        self.gemini = GoogleGemini(
+            require_env("GEMINI_API_KEY")
+        )
 
-    blogpost = read_file(BLOGPOST_FILE)
+    def fetch(self, url: str):
+        # Strip base domain from URL if full URL was given, then strip leading slash
+        page_path = url.replace(self.wiki.base_domain, "").lstrip("/")
+        print(f"→ Fetching wiki page: /{page_path}")
 
-    print(f"→ Translating blog post to {translate_lang} with Gemini...")
+        page, resp = self.wiki.get_page(page_path)
 
-    prompt = (
-        f"Translate the following Markdown blog post into {translate_lang}. "
-        "Preserve all Markdown formatting, headings, links, and code blocks exactly. "
-        "Output only the translated Markdown with no additional commentary.\n\n"
-        f"{blogpost}"
-    )
+        if not page:
+            errors = resp.get("errors", resp)
+            print(f"ERROR: Page not found at '{page_path}': {errors}", file=sys.stderr)
+            sys.exit(1)
 
-    result = gemini_generate(api_key, prompt)
-    write_file(TRANSLATED_FILE, result)
+        write_file(SOURCE_FILE, page["content"])
+        write_file(SOURCE_TITLE_FILE, page["title"])
 
+    def write(self):
+        original_lang = require_env("ORIGINAL_LANG", "Hungarian")
+        instructions = read_file(INSTRUCTIONS_FILE)
+        source = read_file(SOURCE_FILE)
 
-def cmd_upload(args):
-    """Upload TRANSLATED_BLOGPOST.md to Wiki.js under /blog/{kebab-title}."""
-    base  = require_env("WIKI_BASE_DOMAIN")
-    token = require_env("WIKI_TOKEN")
+        print(f"→ Generating blog post in {original_lang} with Gemini...")
 
-    content = read_file(TRANSLATED_FILE)
+        prompt = WRITE_PROMPT_TEMPLATE.format(
+            instructions=instructions,
+            original_lang=original_lang,
+            source=source
+        )
 
-    # Extract H1 title
-    match = re.search(r"^#\s+(.+)", content, re.MULTILINE)
-    if not match:
-        print(f"ERROR: No H1 heading found in {TRANSLATED_FILE}", file=sys.stderr)
-        sys.exit(1)
+        result = self.gemini.generate(prompt)
+        write_file(BLOGPOST_FILE, result)
 
-    title     = match.group(1).strip()
-    content   = re.sub(r"^#\s+.+\n?", "", content, count=1, flags=re.MULTILINE).lstrip("\n")
-    kebab     = to_kebab(title)
-    page_path = f"blog/{kebab}"
+    def translate(self):
+        translate_lang = require_env("TRANSLATE_LANG", "English")
+        blogpost = read_file(BLOGPOST_FILE)
 
-    print(f"→ Uploading to Wiki.js")
-    print(f"  Title : {title}")
-    print(f"  Path  : /{page_path}")
+        print(f"→ Translating blog post to {translate_lang} with Gemini...")
 
-    # Check if page already exists
-    find_query = """
-    query ($path: String!) {
-      pages {
-        singleByPath(path: $path, locale: "en") {
-          id
-        }
-      }
-    }
-    """
-    find_resp = wiki_graphql(base, token, find_query, {"path": page_path})
-    existing  = find_resp.get("data", {}).get("pages", {}).get("singleByPath")
-    existing_id = existing.get("id") if existing else None
+        prompt = TRANSLATE_PROMPT_TEMPLATE.format(
+            translate_lang=translate_lang,
+            blogpost=blogpost
+        )
 
-    if existing_id:
-        print(f"  Found existing page id={existing_id}, updating...")
-        mutation = """
-        mutation ($id: Int!, $content: String!) {
-          pages {
-            update(id: $id, content: $content, tags: ["blog"]) {
-              responseResult { succeeded message }
-            }
-          }
-        }
-        """
-        variables = {"id": existing_id, "content": content}
-        resp = wiki_graphql(base, token, mutation, variables)
-        result = resp.get("data", {}).get("pages", {}).get("update", {}).get("responseResult", {})
-    else:
-        print("  Page not found, creating new...")
-        mutation = """
-        mutation ($path: String!, $title: String!, $content: String!) {
-          pages {
-            create(
-              path: $path
-              title: $title
-              content: $content
-              editor: "markdown"
-              locale: "en"
-              isPublished: true
-              isPrivate: false
-              tags: ["blog"]
-              description: ""
-            ) {
-              responseResult { succeeded message }
-              page { id }
-            }
-          }
-        }
-        """
-        variables = {"path": page_path, "title": title, "content": content}
-        resp = wiki_graphql(base, token, mutation, variables)
-        result = resp.get("data", {}).get("pages", {}).get("create", {}).get("responseResult", {})
+        result = self.gemini.generate(prompt)
+        write_file(TRANSLATED_FILE, result)
 
-    errors = resp.get("errors")
-    if errors:
-        print(f"ERROR: {json.dumps(errors, indent=2)}", file=sys.stderr)
-        sys.exit(1)
+    def upload(self):
+        content = read_file(TRANSLATED_FILE)
+        description = read_file(SOURCE_TITLE_FILE).strip()
 
-    if not result.get("succeeded"):
-        print(f"ERROR: Operation failed: {result.get('message')}", file=sys.stderr)
-        sys.exit(1)
+        # Extract H1 title
+        match = re.search(r"^#\s+(.+)", content, re.MULTILINE)
+        if not match:
+            print(f"ERROR: No H1 heading found in {TRANSLATED_FILE}", file=sys.stderr)
+            sys.exit(1)
 
-    print(f"✓ Successfully uploaded to {base}/{page_path}")
+        title = match.group(1).strip()
+        content = re.sub(r"^#\s+.+\n?", "", content, count=1, flags=re.MULTILINE).lstrip("\n")
+        kebab = to_kebab(title)
+        page_path = f"blog/{kebab}"
+
+        print(f"→ Uploading to Wiki.js")
+        print(f"  Title      : {title}")
+        print(f"  Path       : /{page_path}")
+        print(f"  Description: {description}")
+
+        existing_id = self.wiki.find_page_id(page_path)
+
+        if existing_id:
+            print(f"  Found existing page id={existing_id}, updating...")
+            result, resp = self.wiki.update_page(existing_id, content, description)
+        else:
+            print("  Page not found, creating new...")
+            result, resp = self.wiki.create_page(page_path, title, content, description)
+
+        errors = resp.get("errors")
+        if errors:
+            print(f"ERROR: {json.dumps(errors, indent=2)}", file=sys.stderr)
+            sys.exit(1)
+
+        if not result.get("succeeded"):
+            print(f"ERROR: Operation failed: {result.get('message')}", file=sys.stderr)
+            sys.exit(1)
+
+        print(f"✓ Successfully uploaded to {self.wiki.base_domain}/{page_path}")
+
+    def clean(self):
+        """Delete all .md files in the output directory."""
+        if not os.path.exists(OUTPUT_DIR):
+            print(f"→ Output directory '{OUTPUT_DIR}' does not exist. Nothing to clean.")
+            return
+
+        print(f"→ Cleaning {OUTPUT_DIR}/...")
+        count = 0
+        for filename in os.listdir(OUTPUT_DIR):
+            if filename.endswith(".md") or filename.endswith(".txt"):
+                os.remove(os.path.join(OUTPUT_DIR, filename))
+                count += 1
+        print(f"✓ Removed {count} Markdown files.")
 
 
 # ---------------------------------------------------------------------------
@@ -294,22 +345,32 @@ def main():
     # fetch
     p_fetch = subparsers.add_parser("fetch", help="Download a Wiki.js page as Markdown")
     p_fetch.add_argument("url", help="Page path or full URL, e.g. /my-page or https://wiki.example.com/my-page")
-    p_fetch.set_defaults(func=cmd_fetch)
 
     # write
-    p_write = subparsers.add_parser("write", help=f"Generate blog post from {SOURCE_FILE} using Gemini")
-    p_write.set_defaults(func=cmd_write)
+    subparsers.add_parser("write", help=f"Generate blog post using Gemini")
 
     # translate
-    p_translate = subparsers.add_parser("translate", help=f"Translate {BLOGPOST_FILE} using Gemini")
-    p_translate.set_defaults(func=cmd_translate)
+    subparsers.add_parser("translate", help=f"Translate generated blog post using Gemini")
 
     # upload
-    p_upload = subparsers.add_parser("upload", help=f"Upload {TRANSLATED_FILE} to Wiki.js")
-    p_upload.set_defaults(func=cmd_upload)
+    subparsers.add_parser("upload", help=f"Upload translated blog post to Wiki.js")
+
+    # clean
+    subparsers.add_parser("clean", help=f"Delete all .md files in the {OUTPUT_DIR} directory")
 
     args = parser.parse_args()
-    args.func(args)
+    writer = BlogWriter()
+
+    if args.command == "fetch":
+        writer.fetch(args.url)
+    elif args.command == "write":
+        writer.write()
+    elif args.command == "translate":
+        writer.translate()
+    elif args.command == "upload":
+        writer.upload()
+    elif args.command == "clean":
+        writer.clean()
 
 
 if __name__ == "__main__":