From 0ba75df877e189dfcde4f33e14960f77ca075e52 Mon Sep 17 00:00:00 2001
From: Tyler Goodlet <jgbt@protonmail.com>
Date: Fri, 22 Sep 2023 13:53:18 -0400
Subject: [PATCH] Add `data.match_from_pairs` fuzzy symbology scanner

A helper for scanning a "pairs table" that most backends should expose
as part of their (internal) symbology set using `rapidfuzz` over
a `dict[str, Struct]` input table.

Also expose the `data.types.Struct` at the subpkg top level.
---
 piker/data/__init__.py  |  3 +++
 piker/data/_symcache.py | 40 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 42 insertions(+), 1 deletion(-)

diff --git a/piker/data/__init__.py b/piker/data/__init__.py
index 9b12697e9..25c2912a5 100644
--- a/piker/data/__init__.py
+++ b/piker/data/__init__.py
@@ -43,8 +43,10 @@
     SymbologyCache,
     open_symcache,
     get_symcache,
+    match_from_pairs,
 )
 from ._sampling import open_sample_stream
+from ..types import Struct
 
 
 __all__: list[str] = [
@@ -62,6 +64,7 @@
     'open_symcache',
     'open_sample_stream',
     'get_symcache',
+    'Struct',
     'SymbologyCache',
     'types',
 ]
diff --git a/piker/data/_symcache.py b/piker/data/_symcache.py
index 1ba724a2f..44057e89d 100644
--- a/piker/data/_symcache.py
+++ b/piker/data/_symcache.py
@@ -308,7 +308,7 @@ def search(
         matches in a `dict` including the `MktPair` values.
 
         '''
-        matches = fuzzy.extractBests(
+        matches = fuzzy.extract(
             pattern,
             getattr(self, table),
             score_cutoff=50,
@@ -466,3 +466,41 @@ async def sched_gen_symcache():
         pdbp.xpm()
 
     return symcache
+
+
+def match_from_pairs(
+    pairs: dict[str, Struct],
+    query: str,
+    score_cutoff: int = 50,
+
+) -> dict[str, Struct]:
+    '''
+    Fuzzy search over a "pairs table" maintained by most backends
+    as part of their symbology-info caching internals.
+
+    Scan the native symbol key set and return best ranked
+    matches back in a new `dict`.
+
+    '''
+
+    # TODO: somehow cache this list (per call) like we were in
+    # `open_symbol_search()`?
+    keys: list[str] = list(pairs)
+    matches: list[tuple[
+        Sequence[Hashable],  # matching input key
+        Any,  # scores
+        Any,
+    ]] = fuzzy.extract(
+        # NOTE: most backends provide keys uppercased
+        query=query,
+        choices=keys,
+        score_cutoff=score_cutoff,
+    )
+
+    # pop and repack pairs in output dict
+    matched_pairs: dict[str, Pair] = {}
+    for item in matches:
+        pair_key: str = item[0]
+        matched_pairs[pair_key] = pairs[pair_key]
+
+    return matched_pairs