Support Math alphabets (#51)

- Correctly show \bar (#52)

.travis.yml

@@ -16,7 +16,7 @@ matrix:
 
 branches:
   except:
-    - /^[0-9]+\.[0-9]+\.[0-9]+$/
+    - /^[0-9]+\.[0-9]+\.[0-9]+/
 
 install:
   - pip install pipenv

CHANGELOG.md

@@ -2,6 +2,13 @@
 
 ## Unreleased
 
+## 2.7.0 - 2019-06-05
+### Added
+- Support Math alphabets (#51)
+
+### Fixed
+- Correctly show \bar (#52)
+
 ## 2.6.7 - 2019-04-03
 ### Removed
 - Drop Python 3.4 support

Pipfile

@@ -4,8 +4,8 @@ url = "https://pypi.org/simple"
 verify_ssl = true
 
 [dev-packages]
-codecov = "*"
-pytest = "*"
-pytest-cov = "*"
+codecov = "==2.0.15"
+pytest = "==4.6.2"
+pytest-cov = "==2.7.1"
 
 [packages]

appveyor.yml

@@ -11,7 +11,7 @@ environment:
 
 branches:
   except:
-    - /^[0-9]+\.[0-9]+\.[0-9]+$/
+    - /^[0-9]+\.[0-9]+\.[0-9]+/
 
 install:
   - "%PYTHON%\\Scripts\\pip.exe install pipenv"

latex2mathml/commands.py

@@ -31,6 +31,7 @@
     r'\left': (1, 'mo', {'stretchy': 'true', 'fence': 'true', 'form': 'prefix'}),
     r'\right': (1, 'mo', {'stretchy': 'true', 'fence': 'true', 'form': 'postfix'}),
     r'\overline': (1, 'mover', {}),
+    r'\bar': (1, 'mover', {}),
     r'\underline': (1, 'munder', {}),
 }
 

latex2mathml/converter.py

@@ -140,7 +140,7 @@ def _convert_command(element, elements, index, iterable, parent):
             else:
                 _classify(param, new_parent)
     _get_postfix_element(element, parent)
-    if element == r'\overline':
+    if element in (r'\overline', r'\bar'):
         mo = eTree.SubElement(new_parent, 'mo', stretchy='true')
         mo.text = '¯'
     elif element == r'\underline':

latex2mathml/tokenizer.py

@@ -66,7 +66,9 @@ def tokenize(data):
                     yield buffer
                     buffer = ''
             elif char in '{}*':
-                if buffer.startswith(r'\begin') or buffer.startswith(r'\end'):
+                # FIXME: Anything that starts with '\math' passes. There is a huge list of math symbols in
+                #  unimathsymbols.txt and hard-coding all of them is inefficient.
+                if buffer.startswith(r'\begin') or buffer.startswith(r'\end') or buffer.startswith(r'\math'):
                     if buffer.endswith('}'):
                         yield buffer
                         yield char

setup.py

@@ -1,6 +1,6 @@
 from setuptools import setup
 
-VERSION = '2.6.7'
+VERSION = '2.7.0'
 
 setup(
     name='latex2mathml',

tests/test_command.py

@@ -400,3 +400,26 @@ def test_array_with_horizontal_lines(math_and_row):
     s = r'\begin{array}{cr} 1 & 2 \\ 3 & 4 \\ \hline 5 & 6 \end{array}'
 
     assert _convert(math) == convert(s)
+
+
+def test_issue_52(math_and_row):
+    math, row = math_and_row
+    over = eTree.SubElement(row, 'mover')
+    equal = eTree.SubElement(row, 'mo')
+    equal.text = '='
+    sub_right = eTree.SubElement(row, 'msub')
+
+    row = eTree.SubElement(over, 'mrow')
+    sub_left = eTree.SubElement(row, 'msub')
+    mi = eTree.SubElement(sub_left, 'mi')
+    mi.text = 'z'
+    mn = eTree.SubElement(sub_left, 'mn')
+    mn.text = '1'
+    mo = eTree.SubElement(over, 'mo', stretchy='true')
+    mo.text = '¯'
+
+    mi = eTree.SubElement(sub_right, 'mi')
+    mi.text = 'z'
+    mn = eTree.SubElement(sub_right, 'mn')
+    mn.text = '2'
+    assert _convert(math) == convert(r'\bar{z_1} = z_2')

tests/test_converter.py

@@ -438,3 +438,10 @@ def test_issue_33(math_and_row):
     mo = eTree.SubElement(row, 'mo')
     mo.text = ']'
     assert _convert(math) == convert(latex)
+
+
+def test_issue_51(math_and_row):
+    math, row = math_and_row
+    mi = eTree.SubElement(row, 'mi')
+    mi.text = 'ℝ'
+    assert _convert(math) == convert(r'\mathbb{R}')

tests/test_tokenizer.py

@@ -117,3 +117,7 @@ def test_issue_33():
                 '&', '\\vdots', '&', '\\ddots', '&', '\\vdots', '\\\\', 'a', '_', '{', 'm', ',', '1', '}', '&', 'a',
                 '_', '{', 'm', ',', '2', '}', '&', '\\cdots', '&', 'a', '_', '{', 'm', ',', 'n', '}', '\\end{bmatrix}']
     assert expected == list(tokenize(latex))
+
+
+def test_issue_51():
+    assert [r'\mathbb{R}'] == list(tokenize(r'\mathbb{R}'))