Support sup and sub html tags

ChangeLog.rst

@@ -15,6 +15,7 @@ UNRELEASED
 * Support for Python 3.10.
 * Fix #320 padding empty tables and tables with no </tr> tags.
 * Add ``ignore_mailto_links`` config option to ignore ``mailto:`` style links.
+* Feature #407: Support the superscript and subscript tags.
 
 
 

docs/usage.md

@@ -136,6 +136,7 @@ Command line options
 | `--single-line-break`                                  | Use a single line break after a block element rather than two.
 | `--reference-links`                                    | Use reference links instead of inline links to create markdown
 | `--ignore-emphasis`                                    | Ignore all emphasis formatting in the html.
+| `--include-sup-sub`                                    | Include `<sub>` and `<sub>` tags.
 | `-e`, `--asterisk-emphasis`                            | Use asterisk rather than underscore to emphasize text
 | `--unicode-snob`                                       | Use unicode throughout instead of ASCII
 | `--no-automatic-links`                                 | Do not use automatic links like <https://www.google.com/>

html2text/__init__.py

@@ -86,6 +86,7 @@ def __init__(
         self.tag_callback = None
         self.open_quote = config.OPEN_QUOTE  # covered in cli
         self.close_quote = config.CLOSE_QUOTE  # covered in cli
+        self.include_sup_sub = config.INCLUDE_SUP_SUB  # covered in cli
 
         if out is None:
             self.out = self.outtextf
@@ -716,6 +717,12 @@ def link_url(self: HTML2Text, link: str, title: str = "") -> None:
                     self.out("\n[/code]")
             self.p()
 
+        if tag in ["sup", "sub"] and self.include_sup_sub:
+            if start:
+                self.o("<{}>".format(tag))
+            else:
+                self.o("</{}>".format(tag))
+
     # TODO: Add docstring for these one letter functions
     def pbr(self) -> None:
         "Pretty print has a line break"

html2text/_typing.py

@@ -1,3 +1,2 @@
 class OutCallback:
-    def __call__(self, s: str) -> None:
-        ...
+    def __call__(self, s: str) -> None: ...

html2text/cli.py

@@ -264,6 +264,13 @@ class bcolors:
     )
     p.add_argument("filename", nargs="?")
     p.add_argument("encoding", nargs="?", default="utf-8")
+    p.add_argument(
+        "--include-sup-sub",
+        dest="include_sup_sub",
+        action="store_true",
+        default=config.INCLUDE_SUP_SUB,
+        help="Include the sup and sub tags",
+    )
     args = p.parse_args()
 
     if args.filename and args.filename != "-":
@@ -318,5 +325,6 @@ class bcolors:
     h.default_image_alt = args.default_image_alt
     h.open_quote = args.open_quote
     h.close_quote = args.close_quote
+    h.include_sup_sub = args.include_sup_sub
 
     sys.stdout.write(h.handle(html))

html2text/config.py

@@ -163,3 +163,6 @@
 # Use double quotation marks when converting the <q> tag.
 OPEN_QUOTE = '"'
 CLOSE_QUOTE = '"'
+
+# Include the <sup> and <sub> tags
+INCLUDE_SUP_SUB = False

test/sub_tag.html

@@ -0,0 +1,4 @@
+<p>
+  According to the computations by Nakamura, Johnson, and Mason<sub>1</sub> this
+  will result in the complete annihilation of both particles.
+</p>

test/sub_tag.md

@@ -0,0 +1,2 @@
+According to the computations by Nakamura, Johnson, and Mason<sub>1</sub> this
+will result in the complete annihilation of both particles.

test/sup_tag.html

@@ -0,0 +1,4 @@
+<p>
+  One of the most common equations in all of physics is <var>E</var>=<var>m</var
+  ><var>c</var><sup>2</sup>.
+</p>

test/sup_tag.md

@@ -0,0 +1 @@
+One of the most common equations in all of physics is E=mc<sup>2</sup>.

test/test_html2text.py

@@ -140,6 +140,11 @@ def generate_testdata():
             # CLI doesn't support baseurl.
             cmdline_args = skip
 
+        if base_fn in ["sup_tag.html", "sub_tag.html"]:
+            module_args["include_sup_sub"] = True
+            cmdline_args.append("--include-sup-sub")
+            func_args = skip
+
         yield fn, module_args, cmdline_args, func_args
 
 
@@ -201,7 +206,6 @@ def test_command(fn, cmdline_args):
     actual = out.decode()
 
     actual = cleanup_eol(actual)
-
     assert actual.rstrip() == expected.rstrip()