From 93e467933a7eec84341ed08f694f00545397b29d Mon Sep 17 00:00:00 2001
From: lukaszmalinowski14 <lukaszmalinowski14@gmail.com>
Date: Thu, 17 Aug 2023 13:51:31 +0200
Subject: [PATCH] "DFSDF"

---
 langdata/okfonts.txt   |  1 +
 run.py                 |  3 +++
 split_training_text.py | 15 ++++++++-------
 tesseract              |  2 +-
 4 files changed, 13 insertions(+), 8 deletions(-)
 create mode 100644 run.py

diff --git a/langdata/okfonts.txt b/langdata/okfonts.txt
index 164279b..889129c 100644
--- a/langdata/okfonts.txt
+++ b/langdata/okfonts.txt
@@ -690,6 +690,7 @@ BPG Chveulebrivi Bold
 BPG Chveulebrivi Regular
 BPG Courier Bold
 BPG Courier Regular
+BPG CourierETT
 BPG Elite Bold
 BPG Elite Regular
 BPG Glaho Bold
diff --git a/run.py b/run.py
new file mode 100644
index 0000000..94e8875
--- /dev/null
+++ b/run.py
@@ -0,0 +1,3 @@
+import os
+os.environ["TESSDATA_PREFIX"] = "C:/Python/ocr_10/tesseract_tutorial/tesseract/tessdata make training MODEL_NAME=Courier START_MODEL=eng TESSDATA=C:/Python/ocr_10/tesseract_tutorial/tesseract/tessdata MAX_ITERATIONS=100"
+print("END")
diff --git a/split_training_text.py b/split_training_text.py
index 04049c1..ce8bbcb 100755
--- a/split_training_text.py
+++ b/split_training_text.py
@@ -7,11 +7,12 @@
 
 lines = []
 
-with open(training_text_file, 'r') as input_file:
+with open(training_text_file, 'r', encoding="utf-8") as input_file:
     for line in input_file.readlines():
         lines.append(line.strip())
 
-output_directory = 'tesstrain/data/Apex-ground-truth'
+# output_directory = 'tesstrain/data/Apex-ground-truth'
+output_directory = 'tesstrain/data/CourierETT-ground-truth'
 
 if not os.path.exists(output_directory):
     os.mkdir(output_directory)
@@ -19,21 +20,21 @@
 random.shuffle(lines)
 
 count = 100
-
 lines = lines[:count]
-
 line_count = 0
 for line in lines:
     training_text_file_name = pathlib.Path(training_text_file).stem
-    line_training_text = os.path.join(output_directory, f'{training_text_file_name}_{line_count}.gt.txt')
-    with open(line_training_text, 'w') as output_file:
+    line_training_text = os.path.join(
+        output_directory, f'{training_text_file_name}_{line_count}.gt.txt')
+    with open(line_training_text, 'w', encoding="utf-8") as output_file:
         output_file.writelines([line])
 
     file_base_name = f'eng_{line_count}'
 
     subprocess.run([
         'text2image',
-        '--font=Apex',
+        # '--font=Apex',
+        '--font=CourierETT',
         f'--text={line_training_text}',
         f'--outputbase={output_directory}/{file_base_name}',
         '--max_pages=1',
diff --git a/tesseract b/tesseract
index aee19fc..c3edb43 160000
--- a/tesseract
+++ b/tesseract
@@ -1 +1 @@
-Subproject commit aee19fcf8eb832bb9b6a67ada671d3e7679abeac
+Subproject commit c3edb4352bf43367b23b28b130570cb8c4b3b5e7