added in wrapping on zero width space to better support word wrapping in languages like Thai

CHANGELOG.md

@@ -18,6 +18,7 @@ This can also be enabled programmatically with `warnings.simplefilter('default',
 
 ## [2.7.10] - Not released yet
 ### Added
+* Wrapping words on spaces now considers all common space symbols in addition to regular spaces (' '), addressing issues with word-wrapping for languages like Thai, as per [#1190](https://github.com/py-pdf/fpdf2/issues/1190) and [#1191](https://github.com/py-pdf/fpdf2/pull/1191).
 * [`Templates`](https://py-pdf.github.io/fpdf2/fpdf/Templates.html) can now be also defined in JSON files.
 * support to optionally set `wrapmode` in templates (default `"WORD"` can optionally be set to `"CHAR"` to support wrapping on characters for scripts like Chinese or Japanese) - _cf._ [#1159](https://github.com/py-pdf/fpdf2/issues/1159) - thanks to @carlhiggs
 * support for quadratic and cubic Bézier curves with [`FPDF.bezier()`](https://py-pdf.github.io/fpdf2/fpdf/Shapes.html#fpdf.fpdf.FPDF.bezier) - thanks to @awmc000

fpdf/line_break.py

@@ -18,6 +18,24 @@
 SOFT_HYPHEN = "\u00ad"
 HYPHEN = "\u002d"
 SPACE = " "
+BREAKING_SPACE_SYMBOLS = [
+    " ",
+    "\u200b",  # | ZERO WIDTH SPACE
+    "\u2000",  # | EN QUAD
+    "\u2001",  # | EM QUAD
+    "\u2002",  # | EN SPACE
+    "\u2003",  # | EM SPACE
+    "\u2004",  # | THREE-PER-EM SPACE
+    "\u2005",  # | FOUR-PER-EM SPACE
+    "\u2006",  # | SIX-PER-EM SPACE
+    "\u2008",  # | PUNCTUATION SPACE
+    "\u2009",  # | THIN SPACE
+    "\u200A",  # | HAIR SPACE
+    "\u205F",  # | MEDIUM MATHEMATICAL SPACE
+    "\u3000",  # | IDEOGRAPHIC SPACE
+    "\u0009",  # | TAB
+]
+BREAKING_SPACE_SYMBOLS_STR = "".join(BREAKING_SPACE_SYMBOLS)
 NBSP = "\u00a0"
 NEWLINE = "\n"
 FORM_FEED = "\u000c"
@@ -449,7 +467,7 @@ def add_character(
             self.fragments.append(Fragment("", graphics_state, k, url))
         active_fragment = self.fragments[-1]
 
-        if character == SPACE:
+        if character in BREAKING_SPACE_SYMBOLS_STR:
             self.space_break_hint = SpaceHint(
                 original_fragment_index,
                 original_character_index,
@@ -668,7 +686,9 @@ def get_line(self):
                     trailing_form_feed=character == FORM_FEED,
                 )
             if current_line.width + character_width > max_width:
-                if character == SPACE:  # must come first, always drop a current space.
+                if (
+                    character in BREAKING_SPACE_SYMBOLS_STR
+                ):  # must come first, always drop a current space.
                     self.character_index += 1
                     return current_line.manual_break(self.align)
                 if self.wrapmode == WrapMode.CHAR:

test/fonts/test_wraps_zerowidthspace.py

@@ -0,0 +1,28 @@
+from pathlib import Path
+
+from fpdf import FPDF
+
+from test.conftest import assert_pdf_equal
+
+HERE = Path(__file__).resolve().parent
+
+
+def test_wraps_zerowidthspace(tmp_path):
+    pdf = FPDF()
+    pdf.add_font(fname=HERE / "Waree.ttf")
+    pdf.set_font("Waree", size=12)
+    pdf.add_page()
+    pdf.write(
+        8,
+        "Thai (ideally wouldn't wrap after the space after '1000'): "
+        + "นโยบาย\u200Bสาธารณะ\u200Bมี\u200Bความ\u200Bสำคัญ\u200Bต่อ\u200B"
+        + "การ\u200Bสนับสนุน\u200Bการ\u200Bออก\u200Bแบบ\u200Bและ\u200Bการ"
+        + "\u200Bสร้าง\u200Bชุมชน\u200Bและ\u200Bเมือง\u200Bสุขภาพ\u200Bดี\u200B"
+        + "และ\u200Bยั่งยืน รายการ\u200Bตรวจ\u200Bสอบนโยบาย\u200Bความ\u200B"
+        + "ท้าทาย 1,000 เมือง\u200Bสำหรับ\u200Bใช้\u200Bเพื่อ\u200Bประเมิน\u200Bการ"
+        + "\u200Bมี\u200Bอยู่\u200Bและ\u200Bคุณภาพ\u200Bของ\u200Bนโยบาย\u200Bที่"
+        + "\u200Bสอด\u200Bคล้อง\u200Bกับ\u200Bหลัก\u200Bฐาน\u200Bและ\u200Bหลัก"
+        + "\u200Bการ\u200Bสำหรับ\u200Bเมือง\u200Bที่\u200Bมี\u200Bสุขภาพ\u200Bดี"
+        + "\u200Bและ\u200Bยั่งยืน",
+    )
+    assert_pdf_equal(pdf, HERE / "thai_wraps_zerowidthspace.pdf", tmp_path)