Initial commit for RedAirsoft VK to TG and MAX poster

src/text_formatter.py

@@ -0,0 +1,96 @@
+from __future__ import annotations
+
+import html
+import re
+from typing import Optional
+from .config import settings
+
+
+def split_message_chunks(text: str, limit: int = 4000) -> list[str]:
+    text = str(text or "").strip()
+    if not text:
+        return []
+    chunks: list[str] = []
+    while len(text) > limit:
+        split_at = text.rfind("\n", 0, limit)
+        if split_at < limit // 2:
+            split_at = text.rfind(" ", 0, limit)
+        if split_at < limit // 2:
+            split_at = limit
+        chunks.append(text[:split_at].strip())
+        text = text[split_at:].strip()
+    if text:
+        chunks.append(text)
+    return chunks
+
+
+def clean_dividers(lines: list[str]) -> list[str]:
+    sep_pattern = re.compile(r"^\s*[━—─\-=\*\#_]{2,}\s*$")
+    return ["" if sep_pattern.match(line) else line for line in lines]
+
+
+def strip_trailing_hashtags(text: str) -> str:
+    lines = text.rstrip().splitlines()
+    while lines and not lines[-1].strip():
+        lines.pop()
+    if not lines:
+        return ""
+    parts = lines[-1].split()
+    if parts and all(part.startswith("#") for part in parts):
+        lines.pop()
+    return "\n".join(lines).rstrip()
+
+
+def format_post_text(
+    raw_text: str,
+    *,
+    parse_mode: str = "html",  # "html" or "plain"
+    header: Optional[str] = None,
+    footer: Optional[str] = None,
+    tags: Optional[str] = None,
+    bold_first_line: bool = True,
+    vk_url: Optional[str] = None,
+) -> str:
+    header = (settings.header_text if header is None else header).strip()
+    footer = (settings.footer_text if footer is None else footer).strip()
+    tags = (settings.common_tags if tags is None else tags).strip()
+
+    body = strip_trailing_hashtags(raw_text)
+    lines = clean_dividers(body.splitlines())
+
+    title_idx: Optional[int] = None
+    for idx, line in enumerate(lines):
+        if line.strip():
+            title_idx = idx
+            break
+
+    formatted_lines: list[str] = []
+    for idx, line in enumerate(lines):
+        if idx == title_idx and bold_first_line and line.strip():
+            if parse_mode == "html":
+                escaped = html.escape(line.strip())
+                formatted_lines.append(f"<b>{escaped}</b>")
+            else:
+                formatted_lines.append(f"**{line.strip()}**")
+            # Blank line after header if next line is not empty
+            if idx + 1 < len(lines) and lines[idx + 1].strip() != "":
+                formatted_lines.append("")
+        else:
+            if parse_mode == "html":
+                formatted_lines.append(html.escape(line))
+            else:
+                formatted_lines.append(line)
+
+    normalized_body = re.sub(r"\n{3,}", "\n\n", "\n".join(formatted_lines)).strip()
+
+    parts: list[str] = []
+    if header:
+        parts.append(html.escape(header) if parse_mode == "html" else header)
+    if normalized_body:
+        parts.append(normalized_body)
+    if footer:
+        parts.append(html.escape(footer) if parse_mode == "html" else footer)
+    if tags:
+        parts.append(html.escape(tags) if parse_mode == "html" else tags)
+
+    return "\n\n".join(part for part in parts if part).strip()