Merge pull request #218 from adan79/master

Configure break long words and on hyphen for maxcolwidths

Author: astanin

README.md

@@ -1063,6 +1063,31 @@ the lines being wrapped would probably be significantly longer than this.
 
 ```
 
+Text is preferably wrapped on whitespaces and right after the hyphens in hyphenated words.
+
+break_long_words (default: True)  If true, then words longer than width will be broken in order to ensure that no lines are longer than width. 
+If it is false, long words will not be broken, and some lines may be longer than width.
+(Long words will be put on a line by themselves, in order to minimize the amount by which width is exceeded.)
+
+break_on_hyphens (default: True) If true, wrapping will occur preferably on whitespaces and right after hyphens in compound words, as it is customary in English. 
+If false, only whitespaces will be considered as potentially good places for line breaks.
+
+```pycon
+>>> print(tabulate([["John Smith", "Middle-Manager"]], headers=["Name", "Title"], tablefmt="grid", maxcolwidths=[None, 5], break_long_words=False))
++------------+---------+
+| Name       | Title   |
++============+=========+
+| John Smith | Middle- |
+|            | Manager |
++------------+---------+
+>>> print(tabulate([["John Smith", "Middle-Manager"]], headers=["Name", "Title"], tablefmt="grid", maxcolwidths=[None, 5], break_long_words=False, break_on_hyphens=False))
++------------+----------------+
+| Name       | Title          |
++============+================+
+| John Smith | Middle-Manager |
++------------+----------------+
+```
+
 ### Adding Separating lines
 One might want to add one or more separating lines to highlight different sections in a table.
 

tabulate/__init__.py

@@ -33,6 +33,15 @@ def _is_file(f):
 # minimum extra space in headers
 MIN_PADDING = 2
 
+# Whether or not to preserve leading/trailing whitespace in data.
+PRESERVE_WHITESPACE = False
+
+# TextWrapper breaks words longer than 'width'.
+_BREAK_LONG_WORDS = True
+# TextWrapper is breaking hyphenated words.
+_BREAK_ON_HYPHENS = True
+
+
 _DEFAULT_FLOATFMT = "g"
 _DEFAULT_INTFMT = ""
 _DEFAULT_MISSINGVAL = ""
@@ -1629,7 +1638,7 @@ def _normalize_tabular_data(tabular_data, headers, showindex="default"):
     return rows, headers, headers_pad
 
 
-def _wrap_text_to_colwidths(list_of_lists, colwidths, numparses=True):
+def _wrap_text_to_colwidths(list_of_lists, colwidths, numparses=True, break_long_words=_BREAK_LONG_WORDS, break_on_hyphens=_BREAK_ON_HYPHENS):
     if len(list_of_lists):
         num_cols = len(list_of_lists[0])
     else:
@@ -1646,7 +1655,7 @@ def _wrap_text_to_colwidths(list_of_lists, colwidths, numparses=True):
                 continue
 
             if width is not None:
-                wrapper = _CustomTextWrap(width=width)
+                wrapper = _CustomTextWrap(width=width, break_long_words=break_long_words, break_on_hyphens=break_on_hyphens)
                 casted_cell = str(cell)
                 wrapped = [
                     "\n".join(wrapper.wrap(line))
@@ -1705,6 +1714,8 @@ def tabulate(
     headersalign=None,
     rowalign=None,
     maxheadercolwidths=None,
+    break_long_words=_BREAK_LONG_WORDS,
+    break_on_hyphens=_BREAK_ON_HYPHENS,
 ):
     """Format a fixed width table for pretty printing.
 
@@ -2247,7 +2258,7 @@ def tabulate(
 
         numparses = _expand_numparse(disable_numparse, num_cols)
         list_of_lists = _wrap_text_to_colwidths(
-            list_of_lists, maxcolwidths, numparses=numparses
+            list_of_lists, maxcolwidths, numparses=numparses, break_long_words=break_long_words, break_on_hyphens=break_on_hyphens
         )
 
     if maxheadercolwidths is not None:
@@ -2261,7 +2272,7 @@ def tabulate(
 
         numparses = _expand_numparse(disable_numparse, num_cols)
         headers = _wrap_text_to_colwidths(
-            [headers], maxheadercolwidths, numparses=numparses
+            [headers], maxheadercolwidths, numparses=numparses, break_long_words=break_long_words, break_on_hyphens=break_on_hyphens
         )[0]
 
     # empty values in the first column of RST tables should be escaped (issue #82)

test/test_api.py

@@ -56,6 +56,8 @@ def test_tabulate_signature():
         ("headersalign", None),
         ("rowalign", None),
         ("maxheadercolwidths", None),
+        ("break_long_words", True),
+        ("break_on_hyphens", True),
     ]
     _check_signature(tabulate, expected_sig)
 

test/test_output.py

@@ -3319,3 +3319,32 @@ def test_preserve_whitespace():
     expected = "\n".join(["h1    h2    h3", "----  ----  ----", "foo   bar   foo"])
     result = tabulate(test_table, table_headers, preserve_whitespace=False)
     assert_equal(expected, result)
+
+def test_break_long_words():
+    "Output: Default table output, with breakwords true."
+    table_headers = ["h1", "h2", "h3"]
+    test_table = [["  foo1", " bar2   ", "foo3"]]
+
+    # Table is not wrapped on 3 letters due to long word
+    expected = "h1    h2    h3\n----  ----  ----\nfoo1  bar2  foo3"
+    result = tabulate(test_table, table_headers, maxcolwidths=3, break_long_words=False)
+    assert_equal(expected, result)
+
+    # Table max width is 3 letters
+    expected = "h1    h2    h3\n----  ----  ----\nf     ba    foo\noo1   r2    3"
+    result = tabulate(test_table, table_headers, maxcolwidths=3, break_long_words=True)
+    assert_equal(expected, result)
+
+def test_break_on_hyphens():
+    "Output: Default table output, with break on hyphens true."
+    table_headers = ["h1", "h2", "h3"]
+    test_table = [["  foo-bar", " bar-bar   ", "foo-foo"]]
+    # Table max width is 5, long lines breaks on hyphens
+    expected = "h1    h2    h3\n----  ----  -----\nfoo   bar-  foo-f\n-bar  bar   oo"
+    result = tabulate(test_table, table_headers, maxcolwidths=5, break_on_hyphens=False)
+    assert_equal(expected, result)
+
+    # Table data is no longer breaks on hyphens
+    expected = "h1    h2    h3\n----  ----  ----\nfoo-  bar-  foo-\nbar   bar   foo"
+    result = tabulate(test_table, table_headers, maxcolwidths=5, break_on_hyphens=True)
+    assert_equal(expected, result)