First deployment

backend/news_service.py

@@ -25,6 +25,49 @@ logger = logging.getLogger(__name__)
 
 PLACEHOLDER_IMAGE_PATH = "/static/images/placeholder.png"
 GENERIC_AI_FALLBACK_URL = "https://placehold.co/1200x630/0f172a/e2e8f0/png?text=AI+News"
+GENERIC_FINANCE_FALLBACK_URL = "https://placehold.co/1200x630/0f172a/e2e8f0/png?text=Market+News"
+
+_FINANCE_TOPIC_TERMS = frozenset(
+    {
+        "finance",
+        "financial",
+        "market",
+        "markets",
+        "stock",
+        "stocks",
+        "share",
+        "shares",
+        "earnings",
+        "investor",
+        "investors",
+        "nasdaq",
+        "nyse",
+        "dow",
+        "s&p",
+        "bank",
+        "banking",
+        "revenue",
+        "profit",
+        "trading",
+        "ipo",
+        "valuation",
+    }
+)
+
+_FINANCE_IMAGE_BLOCKLIST = (
+    "cat",
+    "dog",
+    "pet",
+    "lion",
+    "tiger",
+    "bird",
+    "horse",
+    "portrait",
+    "selfie",
+    "wedding",
+    "food",
+    "nature-only",
+)
 
 
 async def call_perplexity_api(query: str) -> dict | None:
@@ -174,6 +217,43 @@ def parse_translation_response(response: dict) -> dict | None:
     return None
 
 
+def validate_translation_quality(
+    headline: str, summary: str, language_code: str
+) -> tuple[bool, str | None]:
+    text = f"{headline} {summary}".strip()
+    if not headline or not summary:
+        return False, "empty-content"
+    if len(text) < 20:
+        return False, "too-short"
+
+    repeated_runs = re.search(r"(.)\1{6,}", text)
+    if repeated_runs:
+        return False, "repeated-sequence"
+
+    lines = [segment.strip() for segment in re.split(r"[.!?]\s+", text) if segment.strip()]
+    if lines:
+        unique_ratio = len(set(lines)) / len(lines)
+        if unique_ratio < 0.4:
+            return False, "low-unique-content"
+
+    if language_code == "ta":
+        script_hits = sum(1 for char in text if "\u0b80" <= char <= "\u0bff")
+    elif language_code == "ml":
+        script_hits = sum(1 for char in text if "\u0d00" <= char <= "\u0d7f")
+    else:
+        return True, None
+
+    alpha_hits = sum(1 for char in text if char.isalpha())
+    if alpha_hits == 0:
+        return False, "no-alpha-content"
+
+    script_ratio = script_hits / alpha_hits
+    if script_ratio < 0.35:
+        return False, "script-mismatch"
+
+    return True, None
+
+
 async def generate_translations(
     headline: str,
     summary: str,
@@ -200,7 +280,20 @@ async def generate_translations(
             if response:
                 parsed = parse_translation_response(response)
                 if parsed:
-                    translations[language_code] = parsed
+                    is_valid, reason = validate_translation_quality(
+                        parsed["headline"],
+                        parsed["summary"],
+                        language_code,
+                    )
+                    if is_valid:
+                        logger.info("Translation accepted for %s", language_code)
+                        translations[language_code] = parsed
+                    else:
+                        logger.warning(
+                            "Translation rejected for %s: %s",
+                            language_code,
+                            reason,
+                        )
         except Exception:
             logger.exception("Translation generation failed for %s", language_code)
 
@@ -467,7 +560,7 @@ async def fetch_pixabay_image(query: str) -> tuple[str | None, str | None]:
     except Exception:
         logger.exception("Pixabay image retrieval failed")
 
-    return GENERIC_AI_FALLBACK_URL, "Generic AI fallback"
+    return None, None
 
 
 async def fetch_unsplash_image(query: str) -> tuple[str | None, str | None]:
@@ -591,6 +684,15 @@ def get_enabled_providers() -> list[
 
 async def fetch_royalty_free_image(query: str) -> tuple[str | None, str | None]:
     """Fetch royalty-free image using provider chain with fallback."""
+
+    def is_finance_story(text: str) -> bool:
+        lowered = (text or "").lower()
+        return any(term in lowered for term in _FINANCE_TOPIC_TERMS)
+
+    def is_finance_safe_image(image_url: str, credit: str | None) -> bool:
+        haystack = f"{image_url or ''} {credit or ''}".lower()
+        return not any(term in haystack for term in _FINANCE_IMAGE_BLOCKLIST)
+
     # MCP endpoint takes highest priority if configured
     if config.ROYALTY_IMAGE_MCP_ENDPOINT:
         try:
@@ -610,15 +712,35 @@ async def fetch_royalty_free_image(query: str) -> tuple[str | None, str | None]:
 
     # Extract keywords for better image search
     refined_query = extract_image_keywords(query)
+    finance_story = is_finance_story(query)
+    query_variants = [refined_query]
+    if finance_story:
+        query_variants = [
+            f"{refined_query} stock market trading chart finance business",
+            refined_query,
+        ]
 
     # Try each enabled provider in order
-    for provider_name, fetch_fn in get_enabled_providers():
-        try:
-            image_url, credit = await fetch_fn(refined_query)
-            if image_url:
+    for query_variant in query_variants:
+        for provider_name, fetch_fn in get_enabled_providers():
+            try:
+                image_url, credit = await fetch_fn(query_variant)
+                if not image_url:
+                    continue
+                if finance_story and not is_finance_safe_image(image_url, credit):
+                    logger.info(
+                        "Rejected non-finance-safe image from %s for query '%s': %s",
+                        provider_name,
+                        query_variant,
+                        image_url,
+                    )
+                    continue
                 return image_url, credit
-        except Exception:
-            logger.exception("%s image retrieval failed", provider_name.capitalize())
+            except Exception:
+                logger.exception("%s image retrieval failed", provider_name.capitalize())
+
+    if finance_story:
+        return GENERIC_FINANCE_FALLBACK_URL, "Finance-safe fallback"
 
     return None, None