Adding new rule for colon and asterisk combination

Reviewed-by: gtema <artem.goncharov@gmail.com>
Co-authored-by: Hasko, Vladimir <vladimir.hasko@t-systems.com>
Co-committed-by: Hasko, Vladimir <vladimir.hasko@t-systems.com>

otc_doc_convertor/convertor.py

@@ -423,7 +423,7 @@ class OTCDocConvertor:
         ]
         self.rawize_me(soup, rawize_strings)
 
-        # Pandoc seem to be not escaping properly asterists which are
+        # Pandoc seem to be not escaping properly asterisks which are
         # immediately following non word chars
         # (https://docutils.sourceforge.io/docs/ref/rst/restructuredtext.html#toc-entry-44)
         # NOTE(gtema):
@@ -431,12 +431,26 @@ class OTCDocConvertor:
         # escapings above
         # 2. we are not escaping asterisks at the end of the paragraphs (pandoc
         # deals correctly with that)
-        re_escape = re.compile(r"([-:/'\"<\([{])(\*+)(.)")
+        re_escape = re.compile(r"([-/'\"<\([{])(\*+)(.)")
         for p in soup.body.find_all(string=re_escape):
             if p.string and p.parent.name == "p":
                 p.string.replace_with(
                     re.sub(re_escape, r"\1``\2``\3", p.string))
 
+        # Special case for multiple asterisks and colons like ecs:*:*
+        re_escape = re.compile(r"([:])(\*+)")
+        re_escape_new = re.compile(r"([:])(\*)[^$]")
+        for p in soup.body.find_all(string=re_escape):
+            if p.string and (p.parent.name == "p" or p.parent.name == "li"):
+                string = p.string
+                while re.search(re_escape, string):
+                    if re.search(re_escape_new, string):
+                        string = re.sub(
+                            re_escape, r"\1``\2``", string, count=1)
+                    else:
+                        break
+                p.string.replace_with(string)
+
         # Drop parent link at the bottom of the page
         for parent in soup.body.find_all("p", class_="familylinks"):
             parent.decompose()

otc_doc_convertor/tests/unit/test_convertor.py

@@ -65,7 +65,7 @@ class TestConvertor(TestCase):
         Turbo instance, including the permissions for verifying VPCs, subnets,
         and security groups, creating virtual IP addresses and ports, and
         creating security group rules. You must add the following
-        action:<ul><li>"vpc:*:*"</li></ul></li></ul></td>
+        action:<ul><li>"vpc:``*``:``*``"</li></ul></li></ul></td>
         """
         soup = bs4.BeautifulSoup(test_data, 'lxml')
         res = self.convertor.streamline_html(soup, "dummy")
@@ -76,7 +76,7 @@ class TestConvertor(TestCase):
         <ul><li>"dss:*:get",</li><li>"dss:*:list",</li><li>"dss:*:count"</li></ul>
         """
         expected = """
-        <ul><li>"dss:*:get",</li><li>"dss:*:list",</li><li>"dss:*:count"</li></ul>
+        <ul><li>"dss:``*``:get",</li><li>"dss:``*``:list",</li><li>"dss:``*``:count"</li></ul>
         """
         soup = bs4.BeautifulSoup(test_data, 'lxml')
         res = self.convertor.streamline_html(soup, "dummy")
@@ -87,7 +87,7 @@ class TestConvertor(TestCase):
         <ul><li>"vpc:*:*"</li></ul>
         """
         expected = """
-        <ul><li>"vpc:*:*"</li></ul>
+        <ul><li>"vpc:``*``:``*``"</li></ul>
         """
         soup = bs4.BeautifulSoup(test_data, 'lxml')
         res = self.convertor.streamline_html(soup, "dummy")
@@ -163,3 +163,31 @@ class TestConvertor(TestCase):
             str(res.find('td')),
             expected.strip(),
         )
+
+    def test_streamline_html_escape_12(self):
+        test_data= """
+        <p id="dli_03_0101__en-us_topic_0000001174688342_p1256384461610">DLI:*:*:database:databases.dbname</p>
+        """ # noqa
+        expected = """
+        <p id="dli_03_0101__en-us_topic_0000001174688342_p1256384461610">DLI:``*``:``*``:database:databases.dbname</p>
+        """ # noqa
+        soup = bs4.BeautifulSoup(test_data, 'lxml')
+        res = self.convertor.streamline_html(soup, "dummy")
+        self.assertEqual(
+            str(res.find('p')),
+            expected.strip(),
+        )
+
+    def test_streamline_html_escape_13(self):
+        test_data= """
+        <p id="dli_03_0101__en-us_topic_0000001174688342_p4564244131615">DLI:*:*:queue:queues.*</p>
+        """ # noqa
+        expected = """
+        <p id="dli_03_0101__en-us_topic_0000001174688342_p4564244131615">DLI:``*``:``*``:queue:queues.*</p>
+        """ # noqa
+        soup = bs4.BeautifulSoup(test_data, 'lxml')
+        res = self.convertor.streamline_html(soup, "dummy")
+        self.assertEqual(
+            str(res.find('p')),
+            expected.strip(),
+        )

requirements.txt

@@ -1,4 +1,5 @@
-bs4
+bs4>=0.0.1
-lxml
+beautifulsoup4>=4.0 # MIT
-Jinja2
+lxml>=4.9 # BSD-3-Clause
-requests
+Jinja2>=3.1 # BSD-3-Clause
+requests>=2.28 # Apache-2.0

test-requirements.txt

@@ -1 +1,2 @@
-flake8
+flake8>=6.0 # MIT
+stestr>=4.0 # Apache-2.0

tox.ini

@@ -1,6 +1,6 @@
 [tox]
 minversion = 3.6
-envlist = pep8
+envlist = py3,pep8
 skipsdist = True
 ignore_basepython_conflict = True
 
@@ -15,6 +15,8 @@ setenv =
 deps =
     -r{toxinidir}/requirements.txt
     -r{toxinidir}/test-requirements.txt
+commands = stestr run {posargs}
+           stestr slowest
 
 [testenv:pep8]
 commands =