From 53d83d8f54c75efeb90cf3f4672fa7e2ad2d1264 Mon Sep 17 00:00:00 2001
From: Max Bachmann <kontakt@maxbachmann.de>
Date: Tue, 14 Jun 2022 16:14:16 +0200
Subject: [PATCH] replace GPL licensed components

---
 ppocr/metrics/rec_metric.py                   |  5 +--
 .../table/table_metric/table_metric.py        | 41 ++-----------------
 .../vqa/tools/eval_with_label_end2end.py      |  2 +-
 requirements.txt                              |  2 +-
 4 files changed, 8 insertions(+), 42 deletions(-)

diff --git a/ppocr/metrics/rec_metric.py b/ppocr/metrics/rec_metric.py
index 515b9372..6a13129e 100644
--- a/ppocr/metrics/rec_metric.py
+++ b/ppocr/metrics/rec_metric.py
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import Levenshtein
+from rapidfuzz.distance import Levenshtein
 import string
 
 
@@ -45,8 +45,7 @@ class RecMetric(object):
             if self.is_filter:
                 pred = self._normalize_text(pred)
                 target = self._normalize_text(target)
-            norm_edit_dis += Levenshtein.distance(pred, target) / max(
-                len(pred), len(target), 1)
+            norm_edit_dis += Levenshtein.normalized_distance(pred, target)
             if pred == target:
                 correct_num += 1
             all_num += 1
diff --git a/ppstructure/table/table_metric/table_metric.py b/ppstructure/table/table_metric/table_metric.py
index 9aca98ad..923a9c00 100755
--- a/ppstructure/table/table_metric/table_metric.py
+++ b/ppstructure/table/table_metric/table_metric.py
@@ -9,7 +9,7 @@
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # Apache 2.0 License for more details.
 
-import distance
+from rapidfuzz.distance import Levenshtein
 from apted import APTED, Config
 from apted.helpers import Tree
 from lxml import etree, html
@@ -39,17 +39,6 @@ class TableTree(Tree):
 
 
 class CustomConfig(Config):
-    @staticmethod
-    def maximum(*sequences):
-        """Get maximum possible value
-        """
-        return max(map(len, sequences))
-
-    def normalized_distance(self, *sequences):
-        """Get distance from 0 to 1
-        """
-        return float(distance.levenshtein(*sequences)) / self.maximum(*sequences)
-
     def rename(self, node1, node2):
         """Compares attributes of trees"""
         #print(node1.tag)
@@ -58,23 +47,12 @@ class CustomConfig(Config):
         if node1.tag == 'td':
             if node1.content or node2.content:
                 #print(node1.content, )
-                return self.normalized_distance(node1.content, node2.content)
+                return Levenshtein.normalized_distance(node1.content, node2.content)
         return 0.
 
 
 
 class CustomConfig_del_short(Config):
-    @staticmethod
-    def maximum(*sequences):
-        """Get maximum possible value
-        """
-        return max(map(len, sequences))
-
-    def normalized_distance(self, *sequences):
-        """Get distance from 0 to 1
-        """
-        return float(distance.levenshtein(*sequences)) / self.maximum(*sequences)
-
     def rename(self, node1, node2):
         """Compares attributes of trees"""
         if (node1.tag != node2.tag) or (node1.colspan != node2.colspan) or (node1.rowspan != node2.rowspan):
@@ -90,21 +68,10 @@ class CustomConfig_del_short(Config):
                     node1_content = ['####']
                 if len(node2_content) < 3:
                     node2_content = ['####']   
-                return self.normalized_distance(node1_content, node2_content)
+                return Levenshtein.normalized_distance(node1_content, node2_content)
         return 0.
 
 class CustomConfig_del_block(Config):
-    @staticmethod
-    def maximum(*sequences):
-        """Get maximum possible value
-        """
-        return max(map(len, sequences))
-
-    def normalized_distance(self, *sequences):
-        """Get distance from 0 to 1
-        """
-        return float(distance.levenshtein(*sequences)) / self.maximum(*sequences)
-
     def rename(self, node1, node2):
         """Compares attributes of trees"""
         if (node1.tag != node2.tag) or (node1.colspan != node2.colspan) or (node1.rowspan != node2.rowspan):
@@ -120,7 +87,7 @@ class CustomConfig_del_block(Config):
                 while ' ' in node2_content:
                     print(node2_content.index(' '))
                     node2_content.pop(node2_content.index(' '))
-                return self.normalized_distance(node1_content, node2_content)
+                return Levenshtein.normalized_distance(node1_content, node2_content)
         return 0.
 
 class TEDS(object):
diff --git a/ppstructure/vqa/tools/eval_with_label_end2end.py b/ppstructure/vqa/tools/eval_with_label_end2end.py
index b13ffb56..b0fd8436 100644
--- a/ppstructure/vqa/tools/eval_with_label_end2end.py
+++ b/ppstructure/vqa/tools/eval_with_label_end2end.py
@@ -20,7 +20,7 @@ from shapely.geometry import Polygon
 import numpy as np
 from collections import defaultdict
 import operator
-import Levenshtein
+from rapidfuzz.distance import Levenshtein
 import argparse
 import json
 import copy
diff --git a/requirements.txt b/requirements.txt
index b15176db..976d2919 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -6,7 +6,7 @@ lmdb
 tqdm
 numpy
 visualdl
-python-Levenshtein
+rapidfuzz
 opencv-contrib-python==4.4.0.46
 cython
 lxml
-- 
GitLab