Support character based line warpping (py-pdf#649)

CHANGELOG.md

@@ -18,6 +18,7 @@ This can also be enabled programmatically with `warnings.simplefilter('default',
 
 ## [2.6.2] - Not released yet
 ### Added
+* [`FPDF.multi_cell()`](https://pyfpdf.github.io/fpdf2/fpdf/fpdf.html#fpdf.fpdf.FPDF.multi_cell) and [`FPDF.write()`](https://pyfpdf.github.io/fpdf2/fpdf/fpdf.html#fpdf.fpdf.FPDF.write) now accept a `wrapmode` argument for word or character based line wrapping ("WORD"/"CHAR"). 
 - [`FPDF.image()`](https://pyfpdf.github.io/fpdf2/fpdf/fpdf.html#fpdf.fpdf.FPDF.image) has a new `keep_aspect_ratio` optional boolean parameter, to fit it inside a given rectangle: [documentation](https://pyfpdf.github.io/fpdf2/Images.html#fitting-an-image-inside-a-rectangle)
 - new method `FPDF.preload_image()`: [documentation](https://pyfpdf.github.io/fpdf2/fpdf/fpdf.html#fpdf.fpdf.FPDF.preload_image)
 - new translation of the tutorial in [简体中文](https://pyfpdf.github.io/fpdf2/Tutorial-zh.html) - thanks to @Bubbu0129

docs/Text.md

@@ -8,7 +8,7 @@ There are several ways in fpdf to add text to a PDF document, each of which come
 | [`.cell()`](#cell)  | one | yes | no | yes | Inserts a single-line text string within the boundaries of a given box, optionally with background and border. |
 | [`.multi_cell()`](#multi_cell) | several | yes | no | yes | Inserts a multi-line text string within the boundaries of a given box, optionally with background and border. |
 | [`.write()`](#write) | several | no | no | auto | Inserts a multi-line text string within the boundaries of the page margins, starting at the current x/y location (typically the end of the last inserted text). |
-| [`.write_html()`](#write_html) | several | no | yes | auto | From [html.py](HTML.html). An extension to `.write()`, with additional parsing of basic HTML tags.
+| [`.write_html()`](#write_html) | several | no | yes | auto |  An extension to `.write()`, with additional parsing of basic HTML tags.
 
 ## Typographical Limitations
 
@@ -72,9 +72,9 @@ page break is performed before outputting.
 [Signature and parameters for.cell()](https://pyfpdf.github.io/fpdf2/fpdf/fpdf.html#fpdf.fpdf.FPDF.cell)
 
 ## .multi_cell()
-Allows printing text with line breaks. Those can be automatic (breaking at the
-most recent space or soft-hyphen character) as soon as the text reaches the
-right border of the cell, or explicit (via the `\\n` character).
+Allows printing text with word or character based line breaks. Those can be automatic
+(breaking at the most recent space or soft-hyphen character) as soon as the text
+reaches the right border of the cell, or explicit (via the `\\n` character).
 As many cells as necessary are stacked, one below the other.
 Text can be aligned, centered or justified. The cell block can be framed and
 the background painted.
@@ -90,9 +90,12 @@ When `split_only == True`, returns `txt` split into lines in an array (with any
 ## .write()
 Prints multi-line text between the page margins, starting from the current position.
 When the right margin is reached, a line break occurs at the most recent
-space or soft-hyphen character, and text continues from the left margin.
-A manual break happens any time the \\n character is met,
-Upon method exit, the current position is left near the end of the text, ready for the next call to continue without a gap, potentially with a different font or size set. Returns a boolean indicating if page break was triggered.
+space or soft-hyphen character (in word wrap mode) or at the current position (in
+character break mode), and text continues from the left margin.
+A manual break happens any time the \\n character is met.
+Upon method exit, the current position is left near the end of the text, ready for
+the next call to continue without a gap, potentially with a different font or size set.
+Returns a boolean indicating if page break was triggered.
 
 The primary purpose of this method is to print continuously wrapping text, where different parts may be rendered in different fonts or font sizes. This contrasts eg. with `.multi_cell()`, where a change in font family or size can only become effective on a new line.
 

fpdf/enums.py

@@ -99,6 +99,15 @@ def coerce(cls, value):
         raise TypeError(f"{value} cannot convert to a {cls.__name__}")
 
 
+class WrapMode(CoerciveEnum):
+    "Defines how to break and wrap lines in multi-line text."
+    WORD = intern("WORD")
+    "Wrap by word"
+
+    CHAR = intern("CHAR")
+    "Wrap by character"
+
+
 class CharVPos(CoerciveEnum):
     "Defines the vertical position of text relative to the line."
     SUP = intern("SUP")

fpdf/fpdf.py

@@ -69,6 +69,7 @@ class Image:
     FontDescriptorFlags,
     AccessPermission,
     CharVPos,
+    WrapMode,
 )
 from .errors import FPDFException, FPDFPageFormatException, FPDFUnicodeEncodingException
 from .fonts import fpdf_charwidths
@@ -3251,6 +3252,7 @@ def multi_cell(
         print_sh=False,
         new_x=XPos.RIGHT,
         new_y=YPos.NEXT,
+        wrapmode: WrapMode = WrapMode.WORD,
     ):
         """
         This method allows printing text with line breaks. They can be automatic
@@ -3287,13 +3289,16 @@ def multi_cell(
                 of text as bold / italics / underlined. Default to False.
             print_sh (bool): Treat a soft-hyphen (\\u00ad) as a normal printable
                 character, instead of a line breaking opportunity. Default value: False
+            wrapmode (fpdf.enums.WrapMode): "WORD" for word based line wrapping (default),
+                "CHAR" for character based line wrapping.
 
         Using `new_x=XPos.RIGHT, new_y=XPos.TOP, maximum height=pdf.font_size` is
         useful to build tables with multiline text in cells.
 
         Returns: a boolean indicating if page break was triggered,
             or if `split_only == True`: `txt` splitted into lines in an array
         """
+        wrapmode = WrapMode.coerce(wrapmode)
         if isinstance(w, str) or isinstance(h, str):
             raise ValueError(
                 "Parameter 'w' and 'h' must be numbers, not strings."
@@ -3361,6 +3366,7 @@ def multi_cell(
             styled_text_fragments,
             justify=(align == Align.J),
             print_sh=print_sh,
+            wrapmode=wrapmode,
         )
         text_line = multi_line_break.get_line_of_given_width(maximum_allowed_width)
         while (text_line) is not None:
@@ -3476,7 +3482,12 @@ def multi_cell(
 
     @check_page
     def write(
-        self, h: float = None, txt: str = "", link: str = "", print_sh: bool = False
+        self,
+        h: float = None,
+        txt: str = "",
+        link: str = "",
+        print_sh: bool = False,
+        wrapmode: WrapMode = WrapMode.WORD,
     ):
         """
         Prints text from the current position.
@@ -3492,7 +3503,10 @@ def write(
                 (identifier returned by `FPDF.add_link`) or external URL.
             print_sh (bool): Treat a soft-hyphen (\\u00ad) as a normal printable
                 character, instead of a line breaking opportunity. Default value: False
+            wrapmode (fpdf.enums.WrapMode): "WORD" for word based line wrapping (default),
+                "CHAR" for character based line wrapping.
         """
+        wrapmode = WrapMode.coerce(wrapmode)
         if not self.font_family:
             raise FPDFException("No font set, you need to call set_font() beforehand")
         if isinstance(h, str):
@@ -3511,6 +3525,7 @@ def write(
         multi_line_break = MultiLineBreak(
             styled_text_fragments,
             print_sh=print_sh,
+            wrapmode=wrapmode,
         )
         # first line from current x position to right margin
         first_width = self.w - self.x - self.r_margin

fpdf/line_break.py

@@ -8,7 +8,7 @@
 
 from typing import NamedTuple, Any, Union, Sequence
 
-from .enums import CharVPos
+from .enums import CharVPos, WrapMode
 from .errors import FPDFException
 
 SOFT_HYPHEN = "\u00ad"
@@ -306,6 +306,20 @@ def add_character(
             self.width += character_width
             active_fragment.characters.append(character)
 
+    def trim_trailing_spaces(self):
+        if not self.fragments:
+            return
+        last_frag = self.fragments[-1]
+        last_char = last_frag.characters[-1]
+        while last_char == " ":
+            char_width = last_frag.get_character_width(" ")
+            self.width -= char_width
+            last_frag.trim(-1)
+            if not last_frag.characters:
+                del self.fragments[-1]
+            last_frag = self.fragments[-1]
+            last_char = last_frag.characters[-1]
+
     def _apply_automatic_hint(self, break_hint: Union[SpaceHint, HyphenHint]):
         """
         This function mutates the current_line, applying one of the states
@@ -364,10 +378,12 @@ def __init__(
         styled_text_fragments: Sequence,
         justify: bool = False,
         print_sh: bool = False,
+        wrapmode: WrapMode = WrapMode.WORD,
     ):
         self.styled_text_fragments = styled_text_fragments
         self.justify = justify
         self.print_sh = print_sh
+        self.wrapmode = wrapmode
         self.fragment_index = 0
         self.character_index = 0
         self.idx_last_forced_break = None
@@ -405,9 +421,14 @@ def get_line_of_given_width(self, maximum_width: float, wordsplit: bool = True):
                 return current_line.manual_break(trailing_nl=True)
 
             if current_line.width + character_width > maximum_width:
-                if character == SPACE:
+                if character == SPACE:  # must come first, always drop a current space.
                     self.character_index += 1
                     return current_line.manual_break(self.justify)
+                if self.wrapmode == WrapMode.CHAR:
+                    # If the line ends with one or more spaces, then we want to get rid of them
+                    # so it can be justified correctly.
+                    current_line.trim_trailing_spaces()
+                    return current_line.manual_break(self.justify)
                 if current_line.automatic_break_possible():
                     (
                         self.fragment_index,

test/text/test_multi_cell.py

@@ -399,3 +399,22 @@ def test_multi_cell_char_spacing(tmp_path):  # issue #489
     pdf.set_char_spacing(10)
     pdf.multi_cell(w=150, txt=LOREM_IPSUM[:200], new_x="LEFT", fill=True)
     assert_pdf_equal(pdf, HERE / "multi_cell_char_spacing.pdf", tmp_path)
+
+
+def test_multi_cell_char_wrap(tmp_path):  # issue #649
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_font("Helvetica", "", 10)
+    pdf.set_fill_color(255, 255, 0)
+    pdf.multi_cell(w=50, txt=LOREM_IPSUM[:200], new_x="LEFT", fill=True)
+    pdf.ln()
+    pdf.multi_cell(
+        w=50, txt=LOREM_IPSUM[:200], new_x="LEFT", fill=True, wrapmode="CHAR"
+    )
+    pdf.ln()
+    pdf.set_font("Courier", "", 10)
+    txt = "     " + "abcdefghijklmnopqrstuvwxyz" * 3
+    pdf.multi_cell(w=50, txt=txt, new_x="LEFT", fill=True, align="L")
+    pdf.ln()
+    pdf.multi_cell(w=50, txt=txt, new_x="LEFT", fill=True, align="L", wrapmode="CHAR")
+    assert_pdf_equal(pdf, HERE / "multi_cell_char_wrap.pdf", tmp_path)

test/text/test_write.py

@@ -57,7 +57,6 @@ def test_write_font_stretching(tmp_path):  # issue #478
     pdf.add_page()
     # built-in font
     pdf.set_font("Helvetica", "", 8)
-    pdf.set_fill_color(255, 255, 0)
     pdf.set_right_margin(pdf.w - right_boundary)
     pdf.write(txt=LOREM_IPSUM[:100])
     pdf.ln()
@@ -70,7 +69,6 @@ def test_write_font_stretching(tmp_path):  # issue #478
     pdf.set_stretching(100)
     pdf.add_font(fname=FONTS_DIR / "DroidSansFallback.ttf")
     pdf.set_font("DroidSansFallback", "", 8)
-    pdf.set_fill_color(255, 255, 0)
     pdf.write(txt=LOREM_IPSUM[:100])
     pdf.ln()
     pdf.ln()
@@ -129,3 +127,26 @@ def write_this():
     pdf.denom_lift = 1.0
     write_this()
     assert_pdf_equal(pdf, HERE / "write_superscript.pdf", tmp_path)
+
+
+def test_write_char_wrap(tmp_path):  # issue #649
+    right_boundary = 50
+    pdf = fpdf.FPDF()
+    pdf.add_page()
+    pdf.set_right_margin(pdf.w - right_boundary)
+    pdf.set_font("Helvetica", "", 10)
+    pdf.write(txt=LOREM_IPSUM[:200])
+    pdf.ln()
+    pdf.ln()
+    pdf.write(txt=LOREM_IPSUM[:200], wrapmode="CHAR")
+    pdf.ln()
+    pdf.ln()
+    pdf.set_font("Courier", "", 10)
+    txt = "     " + "abcdefghijklmnopqrstuvwxyz" * 3
+    pdf.write(txt=txt)
+    pdf.ln()
+    pdf.ln()
+    pdf.write(txt=txt, wrapmode="CHAR")
+    pdf.line(pdf.l_margin, 10, pdf.l_margin, 130)
+    pdf.line(right_boundary, 10, right_boundary, 130)
+    assert_pdf_equal(pdf, HERE / "write_char_wrap.pdf", tmp_path)