slack_regex: Update Slack text regex capture newlines.

This prep commit modifies the Slack text regex in
`slack_message_conversion.py` to include the newline character (`\n`) as
part of the first and last capture groups.

Previously, the regex in `slack_message_conversion.py` couldn't capture
and reformat strings surrounded by newlines, such as "\n*ABC*\n". This
kind of string is likely not uncommon to be generated by both the Slack
exporter itself or by our Slack message block and attachment formatters
(`render_blocks` and `render_attachments`).

zerver/data_import/slack_message_conversion.py

@@ -48,25 +48,25 @@ SLACK_USERMENTION_REGEX = r"""
 # Hence, ~stri~ke doesn't format the word in Slack, but ~~stri~~ke
 # formats the word in Zulip
 SLACK_STRIKETHROUGH_REGEX = r"""
-                             (^|[ -(]|[+-/]|\*|\_|[:-?]|\{|\[|\||\^)     # Start after specified characters
+                             (\n|^|[ -(]|[+-/]|\*|\_|[:-?]|\{|\[|\||\^)     # Start after specified characters
                              (\~)                                  # followed by an asterisk
                                  ([ -)+-}—]*)([ -}]+)              # any character except asterisk
                              (\~)                                  # followed by an asterisk
-                             ($|[ -']|[+-/]|[:-?]|\*|\_|\}|\)|\]|\||\^)  # ends with specified characters
+                             (\n|$|[ -']|[+-/]|[:-?]|\*|\_|\}|\)|\]|\||\^)  # ends with specified characters
                              """
 SLACK_ITALIC_REGEX = r"""
-                      (^|[ -*]|[+-/]|[:-?]|\{|\[|\||\^|~)
+                      (\n|^|[ -*]|[+-/]|[:-?]|\{|\[|\||\^|~)
                       (\_)
                           ([ -^`~—]*)([ -^`-~]+)                  # any character
                       (\_)
-                      ($|[ -']|[+-/]|[:-?]|\}|\)|\]|\*|\||\^|~)
+                      (\n|$|[ -']|[+-/]|[:-?]|\}|\)|\]|\*|\||\^|~)
                       """
 SLACK_BOLD_REGEX = r"""
-                    (^|[ -(]|[+-/]|[:-?]|\{|\[|\_|\||\^|~)
+                    (\n|^|[ -(]|[+-/]|[:-?]|\{|\[|\_|\||\^|~)
                     (\*)
                         ([ -)+-~—]*)([ -)+-~]+)                   # any character
                     (\*)
-                    ($|[ -']|[+-/]|[:-?]|\}|\)|\]|\_|\||\^|~)
+                    (\n|$|[ -']|[+-/]|[:-?]|\}|\)|\]|\_|\||\^|~)
                     """
 
 

zerver/tests/fixtures/slack_message_conversion.json

@@ -84,6 +84,11 @@
       "name": "italic_and_strike_conversion",
       "input": "_~italic~_ and ~_strike_~",
       "conversion_output": "*~~italic~~* and ~~*strike*~~"
+    },
+    {
+      "name": "new_line_test",
+      "input": "\n*abc*\n",
+      "conversion_output": "\n**abc**\n"
     }
   ]
 }