Match BOM MPNs to longer LCSC/DigiKey orderable codes.

The lookup required an exact catalog string, so family codes like ESP32-S31-WROOM-3 never picked ESP32-S31-WROOM-3-N16R16V and underscore vs slash MPNs never hit DigiKey.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/services/datasheet_finder.py

@@ -81,20 +81,74 @@ def mpn_matches(query: str, candidate: str) -> bool:
     return bool(_PACKING_REMAINDER.match(longer[len(shorter):]))
 
 
+# Base MPNs this long are treated as a manufacturer family code: DigiKey/LCSC
+# orderable strings may add package/temp (24AA025E64 vs 24AA025E64-I/SN).
+# Keep this above short tokens like "10uF" / "CH340" so we do not steal a
+# sibling die's datasheet.
+_MIN_FAMILY_LEN = 7
+
+
+def mpn_query_variants(mpn: str) -> list[str]:
+    """Search strings to try when catalogs spell the same MPN differently."""
+    raw = (mpn or "").strip()
+    if not raw:
+        return []
+    variants: list[str] = []
+    seen: set[str] = set()
+
+    def add(value: str) -> None:
+        value = value.strip()
+        if value and value not in seen:
+            seen.add(value)
+            variants.append(value)
+
+    add(raw)
+    add(raw.replace("_", "/"))
+    add(raw.replace("/", "_"))
+    if "," in raw:
+        add(raw.split(",", 1)[0])
+    if len(_alnum(raw)) > 8 and raw[-1] in "Rr" and raw[-2].isalnum():
+        add(raw[:-1])
+    stripped = _strip_packing_alnum(raw)
+    if stripped:
+        add(stripped)
+    return variants
+
+
+def mpn_catalog_match(query: str, candidate: str) -> bool:
+    """Same part for datasheet lookup: punctuation, packing, or orderable suffix."""
+    if mpn_matches(query, candidate):
+        return True
+    q = _alnum(query)
+    c = _alnum(candidate)
+    if len(q) < _MIN_FAMILY_LEN or not c:
+        return False
+    return c.startswith(q) and len(c) > len(q)
+
+
 def _pick_lcsc_product(mpn: str, products: list[dict]) -> dict | None:
     exact: dict | None = None
     loose: dict | None = None
+    family: dict | None = None
     want = _alnum(mpn)
     for p in products:
-        model = p.get("productModel") or ""
+        model = (
+            p.get("productModel")
+            or p.get("productName")
+            or p.get("productIntroEn")
+            or ""
+        )
         if not model:
             continue
-        if _alnum(model) == want:
+        got = _alnum(model)
+        if got == want:
             exact = p
             break
         if loose is None and mpn_matches(mpn, model):
             loose = p
-    return exact or loose
+        elif family is None and mpn_catalog_match(mpn, model):
+            family = p
+    return exact or loose or family
 
 
 async def _download_pdf(url: str) -> bytes:
@@ -118,7 +172,7 @@ async def _lcsc_search(keyword: str) -> list[dict]:
     ) as client:
         resp = await client.post(
             f"{_LCSC_BASE}/product/query/list",
-            json={"keyword": keyword, "currentPage": 1, "pageSize": 15},
+            json={"keyword": keyword, "currentPage": 1, "pageSize": 30},
         )
         resp.raise_for_status()
         data = resp.json()
@@ -163,10 +217,7 @@ async def _from_lcsc(mpn: str, lcsc_id: str | None) -> DatasheetHit | None:
         product = None
 
     if product is None:
-        keywords = [mpn]
+        keywords = mpn_query_variants(mpn)
-        stripped = _strip_packing_alnum(mpn)
-        if stripped and stripped.upper() != _alnum(mpn):
-            keywords.append(stripped)
         for keyword in keywords:
             try:
                 products = await _lcsc_search(keyword)

backend/services/digikey.py

@@ -12,6 +12,12 @@ from dataclasses import dataclass, field
 import httpx
 
 from backend.config import settings
+from backend.services.datasheet_finder import (
+    _alnum,
+    mpn_catalog_match,
+    mpn_matches,
+    mpn_query_variants,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -103,31 +109,50 @@ async def _keyword_search(mpn: str) -> list[dict]:
 
 
 def _find_product(mpn: str, products: list[dict]) -> dict | None:
-    """Find the product whose MPN exactly matches ``mpn`` (case/space-insensitive).
+    """Pick a DigiKey product for ``mpn``.
 
-    Returns None when no result has a matching MPN. We intentionally do NOT
+    Prefers punctuation-insensitive equality, then packing suffixes, then a
-    fall back to ``products[0]`` — keyword-search hits without an MPN match
+    longer orderable code that starts with the BOM MPN. Does not fall back
-    are usually for a different part, and silently returning them has
+    to ``products[0]``.
-    polluted the library with wrong specs for non-MPN tokens like ``10uF``.
     """
     if not products:
         return None
 
-    mpn_upper = mpn.upper().replace(" ", "")
+    exact = None
+    loose = None
+    family = None
+    want = _alnum(mpn)
     for product in products:
-        if _get_mpn(product).upper().replace(" ", "") == mpn_upper:
+        cand = _get_mpn(product)
-            return product
+        if not cand:
-    return None
+            continue
+        got = _alnum(cand)
+        if got == want:
+            exact = product
+            break
+        if loose is None and mpn_matches(mpn, cand):
+            loose = product
+        elif family is None and mpn_catalog_match(mpn, cand):
+            family = product
+    return exact or loose or family
 
 
 async def _search_mpn(mpn: str) -> str | None:
     """Search DigiKey for an MPN and return the primary datasheet URL, or None."""
-    products = await _keyword_search(mpn)
+    tried: set[str] = set()
+    for keyword in mpn_query_variants(mpn):
+        key = keyword.upper()
+        if key in tried:
+            continue
+        tried.add(key)
+        products = await _keyword_search(keyword)
         product = _find_product(mpn, products)
         if not product:
-        return None
+            continue
         url = _get_ds_url(product)
-    return url or None
+        if url:
+            return url
+    return None
 
 
 # ---------------------------------------------------------------------------

tests/test_datasheet_finder.py

@@ -9,7 +9,9 @@ from backend.services.datasheet_finder import (
     _pick_lcsc_product,
     _ti_slugs,
     find_datasheet,
+    mpn_catalog_match,
     mpn_matches,
+    mpn_query_variants,
 )
 
 
@@ -18,12 +20,41 @@ def test_mpn_matches_exact_and_packing():
     assert mpn_matches("SPX3819M5-L-3-3", "SPX3819M5-L-3-3/TR")
     assert mpn_matches("MSPM0G3507SPTR", "MSPM0G3507")
     assert mpn_matches("MSPM0G3507", "MSPM0G3507SPTR")
+    assert mpn_matches("25AA1024-I_SM", "25AA1024-I/SM")
     # Variant letter is a different die — must not match
     assert not mpn_matches("CH340", "CH340E")
     assert not mpn_matches("CH340E", "CH340G")
     assert not mpn_matches("TLV9062", "TLV9002")
 
 
+def test_mpn_catalog_match_orderable_suffix():
+    assert mpn_catalog_match("ESP32-S31-WROOM-3", "ESP32-S31-WROOM-3-N16R16V")
+    assert mpn_catalog_match("24AA025E64", "24AA025E64-I/SN")
+    assert mpn_catalog_match("LAN8720A", "LAN8720A-CP-TR")
+    assert mpn_catalog_match("W25Q128JVS", "W25Q128JVSIQ")
+    assert not mpn_catalog_match("CH340", "CH340E")
+    assert not mpn_catalog_match("10uF", "GRM21BR61A106KE19L")
+
+
+def test_mpn_query_variants_underscore_and_reel():
+    variants = mpn_query_variants("25AA1024-I_SM")
+    assert "25AA1024-I/SM" in variants
+    variants = mpn_query_variants("ADAU1467WBCPZ300R")
+    assert "ADAU1467WBCPZ300" in variants
+
+
+def test_pick_lcsc_family_orderable():
+    products = [
+        {
+            "productModel": "ESP32-S31-WROOM-3-N16R16V",
+            "pdfUrl": "http://esp.pdf",
+        },
+    ]
+    picked = _pick_lcsc_product("ESP32-S31-WROOM-3", products)
+    assert picked is not None
+    assert picked["pdfUrl"] == "http://esp.pdf"
+
+
 def test_pick_lcsc_prefers_exact_model():
     products = [
         {"productModel": "TPSPX3819M5-L-3-3", "pdfUrl": "http://a.pdf"},

tests/test_digikey_match.py

@@ -0,0 +1,23 @@
+from backend.services.digikey import _find_product
+
+
+def test_find_product_accepts_underscore_vs_slash():
+    products = [{"ManufacturerProductNumber": "25AA1024-I/SM", "DatasheetUrl": "http://a.pdf"}]
+    picked = _find_product("25AA1024-I_SM", products)
+    assert picked is not None
+    assert picked["DatasheetUrl"] == "http://a.pdf"
+
+
+def test_find_product_accepts_family_orderable():
+    products = [
+        {"ManufacturerProductNumber": "24AA025E64-I/SN", "DatasheetUrl": "http://b.pdf"},
+    ]
+    picked = _find_product("24AA025E64", products)
+    assert picked is not None
+    assert picked["DatasheetUrl"] == "http://b.pdf"
+
+
+def test_find_product_rejects_unrelated():
+    products = [{"ManufacturerProductNumber": "GRM21BR61A106KE19L", "DatasheetUrl": "http://c.pdf"}]
+    assert _find_product("10uF", products) is None
+    assert _find_product("CH340", [{"ManufacturerProductNumber": "CH340E"}]) is None