From c163376f86b24f9c3b29222def88d63e6d922f46 Mon Sep 17 00:00:00 2001
From: Inga Ulusoy <inga.ulusoy@uni-heidelberg.de>
Date: Mon, 2 Dec 2024 13:33:06 +0100
Subject: [PATCH 1/3] manage occurence of full stops in a better way

---
 ammico/test/test_text.py | 13 ++++++++++
 ammico/text.py           | 51 ++++++++++++++++++++++++++++++++++------
 2 files changed, 57 insertions(+), 7 deletions(-)

diff --git a/ammico/test/test_text.py b/ammico/test/test_text.py
index 67ae0c76..5ebb00df 100644
--- a/ammico/test/test_text.py
+++ b/ammico/test/test_text.py
@@ -141,6 +141,19 @@ def test_init_revision_numbers_and_models(accepted):
         tt.TextDetector({}, revision_numbers=["something"], accept_privacy=accepted)
 
 
+def test_check_add_space_after_full_stop(accepted):
+    test_obj = tt.TextDetector({}, accept_privacy=accepted)
+    test_obj.subdict["text"] = "I like cats. I like dogs."
+    test_obj._check_add_space_after_full_stop()
+    assert test_obj.subdict["text"] == "I like cats. I like dogs."
+    test_obj.subdict["text"] = "I like cats."
+    test_obj._check_add_space_after_full_stop()
+    assert test_obj.subdict["text"] == "I like cats."
+    test_obj.subdict["text"] = "www.icanhascheezburger.com"
+    test_obj._check_add_space_after_full_stop()
+    assert test_obj.subdict["text"] == "www. icanhascheezburger. com"
+
+
 @pytest.mark.gcv
 def test_analyse_image(set_testdict, set_environ, accepted):
     for item in set_testdict:
diff --git a/ammico/text.py b/ammico/text.py
index 61499022..b3260bb4 100644
--- a/ammico/text.py
+++ b/ammico/text.py
@@ -4,6 +4,7 @@
 import spacy
 import io
 import os
+import re
 from ammico.utils import AnalysisMethod
 import grpc
 import pandas as pd
@@ -225,6 +226,48 @@ def _initialize_spacy(self):
             spacy.cli.download("en_core_web_md")
             self.nlp = spacy.load("en_core_web_md")
 
+    def _check_add_space_after_full_stop(self):
+        """Add a space after a full stop. Required by googletrans."""
+        # we have found text, now we check for full stops
+        index_stop = [
+            i.start() for i in re.finditer("\.", self.subdict["text"])  # noqa
+        ]
+        if not index_stop:  # no full stops found
+            return
+        # check if this includes the last string item
+        end_of_list = False
+        if len(self.subdict["text"]) <= (index_stop[-1] + 1):
+            # the last found full stop is at the end of the string
+            # but we can include all others
+            if len(index_stop) == 1:
+                end_of_list = True
+            else:
+                index_stop.pop()
+        print(
+            "End of list",
+            end_of_list,
+            len(self.subdict["text"]),
+            index_stop,
+            index_stop[-1] + 1,
+            "text",
+            self.subdict["text"],
+        )
+        if end_of_list:  # only one full stop at end of string
+            return
+        # if this is not the end of the list, check if there is a space after the full stop
+        no_space = [i for i in index_stop if self.subdict["text"][i + 1] != " "]
+        if not no_space:  # all full stops have a space after them
+            return
+        # else, amend the text
+        add_one = 1
+        for i in no_space:
+            self.subdict["text"] = (
+                self.subdict["text"][: i + add_one]
+                + " "
+                + self.subdict["text"][i + add_one :]
+            )
+            add_one += 1
+
     def analyse_image(self) -> dict:
         """Perform text extraction and analysis of the text.
 
@@ -239,13 +282,7 @@ def analyse_image(self) -> dict:
         else:
             # make sure all full stops are followed by whitespace
             # otherwise googletrans breaks
-            index_stop = self.subdict["text"].find(".")
-            if self.subdict["text"][index_stop + 1] != " ":
-                self.subdict["text"] = (
-                    self.subdict["text"][: index_stop + 1]
-                    + " "
-                    + self.subdict["text"][index_stop + 1 :]
-                )
+            self._check_add_space_after_full_stop()
             self.translate_text()
             self.remove_linebreaks()
             if self.analyse_text:

From 9b1eaa3fac7f58be589dc271bdb8e6bfe4b64765 Mon Sep 17 00:00:00 2001
From: Inga Ulusoy <inga.ulusoy@uni-heidelberg.de>
Date: Mon, 2 Dec 2024 14:30:05 +0100
Subject: [PATCH 2/3] bump version

---
 pyproject.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pyproject.toml b/pyproject.toml
index ff1e8516..cbd55bea 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ammico"
-version = "0.2.3"
+version = "0.2.4"
 description = "AI Media and Misinformation Content Analysis Tool"
 readme = "README.md"
 maintainers = [

From fd48428d5ce9544cea757999220513424576fb93 Mon Sep 17 00:00:00 2001
From: Inga Ulusoy <inga.ulusoy@uni-heidelberg.de>
Date: Mon, 2 Dec 2024 14:33:24 +0100
Subject: [PATCH 3/3] cleanup

---
 ammico/text.py | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/ammico/text.py b/ammico/text.py
index b3260bb4..0d020afc 100644
--- a/ammico/text.py
+++ b/ammico/text.py
@@ -243,15 +243,6 @@ def _check_add_space_after_full_stop(self):
                 end_of_list = True
             else:
                 index_stop.pop()
-        print(
-            "End of list",
-            end_of_list,
-            len(self.subdict["text"]),
-            index_stop,
-            index_stop[-1] + 1,
-            "text",
-            self.subdict["text"],
-        )
         if end_of_list:  # only one full stop at end of string
             return
         # if this is not the end of the list, check if there is a space after the full stop