break on newlines instead of crlf

VikParuchuri · Dec 10, 2024 · be036b2 · be036b2
1 parent d053ffa
commit be036b2
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/pdftext/pdf/pages.py b/pdftext/pdf/pages.py
@@ -71,16 +71,16 @@ def line_break():
             line_break()
             continue
 
-        # we break if the previous span ends with a CLRF or hyphenation
-        if any(line["spans"][-1]["text"].endswith(suffix) for suffix in ["\r\n", "\x02"]):
+        # we break if the previous span ends with a linebreak or hyphenation
+        if any(line["spans"][-1]["text"].endswith(suffix) for suffix in ["\n", "\x02"]):
             line_break()
             continue
 
         if span["rotation"] != line["rotation"]:
             line_break()
             continue
 
-        # sometimes pdfium doesn't inject a CLRF at the end of a line, so we check the span positions
+        # sometimes pdfium doesn't inject a linebreak, so we check the span positions
         if span["bbox"].y_start > line["bbox"].y_end:
             line_break()
             continue