From a3e60c639f1de769973814d01a53aaea36771cf8 Mon Sep 17 00:00:00 2001
From: Ben Sturmfels <ben@sturm.com.au>
Date: Mon, 21 Feb 2022 12:16:24 +1100
Subject: [PATCH] reconcile: Add special case for payee first word match.

---
 .../reconcile/prototype_amex_reconciler.py    | 21 +++++++++++++++++--
 tests/test_reconcile.py                       |  8 +++++++
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/conservancy_beancount/reconcile/prototype_amex_reconciler.py b/conservancy_beancount/reconcile/prototype_amex_reconciler.py
index 149c785..2d82576 100644
--- a/conservancy_beancount/reconcile/prototype_amex_reconciler.py
+++ b/conservancy_beancount/reconcile/prototype_amex_reconciler.py
@@ -89,6 +89,7 @@ JUNK_WORDS = [
     'online',
     'donation',
     'usd',
+    'inc',
 ]
 JUNK_WORDS_RES = [re.compile(word, re.IGNORECASE) for word in JUNK_WORDS]
 ZERO_RE = re.compile('^0+')
@@ -182,6 +183,21 @@ def sort_records(records: List) -> List:
     return sorted(records, key=lambda x: (x['date'], x['amount']))
 
 
+def first_word_exact_match(a, b):
+    if len(a) == 0 or len(b) == 0:
+        return 0
+    first_a = a.split()[0].strip()
+    first_b = b.split()[0].strip()
+    if first_a.casefold() == first_b.casefold():
+        return min(1.0, 0.2 * len(first_a))
+    else:
+        return 0;
+
+def payee_match(a, b):
+    fuzzy_match = fuzz.token_set_ratio(a, b) / 100.00
+    first_word_match = first_word_exact_match(a, b)
+    return max(fuzzy_match, first_word_match)
+
 def records_match(r1: Dict, r2: Dict) -> Tuple[bool, str]:
     """Do these records represent the same transaction?"""
 
@@ -204,7 +220,8 @@ def records_match(r1: Dict, r2: Dict) -> Tuple[bool, str]:
     else:
         check_score = 0.0
 
-    payee_score = fuzz.token_set_ratio(r1['payee'], r2['payee']) / 100.00
+    payee_score = payee_match(r1['payee'], r2['payee'])
+
     if check_score == 1.0 or payee_score > 0.8:
         payee_message = ''
     elif payee_score > 0.4:
@@ -387,7 +404,7 @@ def main(args):
 
     out = io.StringIO()
     print('-' * 155)
-    print(f'{"Statement transaction":<38}            {"Books transaction":<44}   Notes')
+    print(f'{"Statement transaction":<52}            {"Books transaction":<58}   Notes')
     print('-' * 155)
     for _, output in sorted(matches):
         print(output)
diff --git a/tests/test_reconcile.py b/tests/test_reconcile.py
index ea9fe8e..7c0ba5d 100644
--- a/tests/test_reconcile.py
+++ b/tests/test_reconcile.py
@@ -6,6 +6,7 @@ from conservancy_beancount.reconcile.prototype_amex_reconciler import (
     remove_payee_junk,
     date_proximity,
     remove_duplicate_words,
+    payee_match,
 )
 
 S1 = {
@@ -178,3 +179,10 @@ def test_date_proximity():
 
 def test_remove_duplicate_words():
     assert remove_duplicate_words('Hi Foo Kow FOO') == 'Hi Foo Kow'
+
+def test_remove_duplicate_words():
+    assert remove_duplicate_words('Hi Foo Kow FOO') == 'Hi Foo Kow'
+
+def test_payee_matches_when_first_word_matches():
+    assert payee_match('Gandi San Francisco', 'Gandi example.com renewal 1234567') == 1.0
+    assert payee_match('USPS 123456789 Portland', 'USPS John Brown') == 0.8