Cleanup implementation

Author: VikParuchuri

pdftext/pdf/chars.py

@@ -88,10 +88,7 @@ def word_break():
         # we break on any change in font info - optimized comparison
         char_font = char['font']
         word_font = word['font']
-        if (char_font['name'] != word_font['name'] or 
-            char_font['flags'] != word_font['flags'] or 
-            char_font['size'] != word_font['size'] or 
-            char_font['weight'] != word_font['weight']):
+        if any(char_font[k] != word_font[k] for k in ['name', 'flags', 'size', 'weight']):
             word_break()
             continue
 

pdftext/pdf/pages.py

@@ -132,11 +132,8 @@ def span_break():
 def get_lines(spans: Spans) -> Lines:
     lines: Lines = []
     line: Line = None
-    line_text: str = ""
 
     def line_break():
-        global line_text
-        line_text = ""
         lines.append({"spans": [span], "bbox": span["bbox"], "rotation": span["rotation"]})
 
     for span in spans:
@@ -147,13 +144,9 @@ def line_break():
             line_break()
             continue
 
-        # we break if the previous span ends with a linebreak, and the line has text
-        if line["spans"][-1]["text"].endswith("\n") and line_text.strip():
-            line_break()
-            continue
-
-        # we break if the current line ends with a hyphen
-        if line["spans"][-1]["text"].endswith("\x02"):
+        # we break if the previous span ends with a linebreak
+        last_text = line["spans"][-1]["text"]
+        if any(last_text.endswith(suffix) for suffix in ["\n", "\x02"]):
             line_break()
             continue
 
@@ -167,7 +160,6 @@ def line_break():
             continue
 
         line["spans"].append(span)
-        line_text += span["text"]
         line["bbox"] = line["bbox"].merge(span["bbox"])
 
     return lines