diff mercurial/utils/stringutil.py @ 37210:2a2ce93e12f4

templatefuncs: add mailmap template function

This commit adds a template function to support the .mailmap file
in Mercurial repositories. The .mailmap file comes from git, and
can be used to map new emails and names for old commits. The general
use case is that someone may change their name or author commits
under different emails and aliases, which would make these
commits appear as though they came from different persons. The
file allows you to specify the correct name that should be used
in place of the author field specified in the commit.

The mailmap file has 4 possible formats used to map old "commit"
names to new "proper" names:

1. <[e-mail]> <[e-mail]>
2. Proper Name <[e-mail]>
3. Proper Name <[e-mail]> <[e-mail]>
4. Proper Name <[e-mail]> Commit Name <[e-mail]>

Essentially there is a commit email present in each mailmap entry,
that maps to either an updated name, email, or both. The final
possible format allows commits authored by a person who used
both an old name and an old email to map to a new name and email.

To parse the file, we split by spaces and build a name out
of every element that does not start with "<". Once we find an element
that does start with "<" we concatenate all the name elements that preceded
and add that as a parsed name. We then add the email as the first
parsed email. We repeat the process until the end of the line, or
a comment is found. We will be left with all parsed names in a list,
and all parsed emails in a list, with the 0 index being the proper
values and the 1 index being the commit values (if they were specified
in the entry).

The commit values are added as the keys to a dict, and with the proper
fields as the values. The mapname function takes the mapping object and
the commit author field and attempts to look for a corresponding entry.
To do so we try (commit name, commit email) first, and if no results are
returned then (None, commit email) is also looked up. This is due to
format 4 from above, where someone may have a mailmap entry with both
name and email, and if they don't it is possible they have an entry that
uses only the commit email.

Differential Revision: https://phab.mercurial-scm.org/D2904

--- a/mercurial/utils/stringutil.py	Fri Mar 30 12:16:46 2018 -0700
+++ b/mercurial/utils/stringutil.py	Mon Mar 19 11:16:21 2018 -0400
@@ -14,6 +14,7 @@
 import textwrap
 
 from ..i18n import _
+from ..thirdparty import attr
 
 from .. import (
     encoding,
@@ -158,6 +159,136 @@
     f = author.find('@')
     return author[:f].replace('.', ' ')
 
+@attr.s(hash=True)
+class mailmapping(object):
+    '''Represents a username/email key or value in
+    a mailmap file'''
+    email = attr.ib()
+    name = attr.ib(default=None)
+
+def parsemailmap(mailmapcontent):
+    """Parses data in the .mailmap format
+
+    >>> mmdata = b"\\n".join([
+    ... b'# Comment',
+    ... b'Name <[e-mail]>',
+    ... b'<[e-mail]> <[e-mail]>',
+    ... b'Name <[e-mail]> <[e-mail]>',
+    ... b'Name <[e-mail]> Commit <[e-mail]>',
+    ... ])
+    >>> mm = parsemailmap(mmdata)
+    >>> for key in sorted(mm.keys()):
+    ...     print(key)
+    mailmapping(email='[e-mail]', name=None)
+    mailmapping(email='[e-mail]', name=None)
+    mailmapping(email='[e-mail]', name=None)
+    mailmapping(email='[e-mail]', name='Commit')
+    >>> for val in sorted(mm.values()):
+    ...     print(val)
+    mailmapping(email='[e-mail]', name='Name')
+    mailmapping(email='[e-mail]', name=None)
+    mailmapping(email='[e-mail]', name='Name')
+    mailmapping(email='[e-mail]', name='Name')
+    """
+    mailmap = {}
+
+    if mailmapcontent is None:
+        return mailmap
+
+    for line in mailmapcontent.splitlines():
+
+        # Don't bother checking the line if it is a comment or
+        # is an improperly formed author field
+        if line.lstrip().startswith('#') or any(c not in line for c in '<>@'):
+            continue
+
+        # name, email hold the parsed emails and names for each line
+        # name_builder holds the words in a persons name
+        name, email = [], []
+        namebuilder = []
+
+        for element in line.split():
+            if element.startswith('#'):
+                # If we reach a comment in the mailmap file, move on
+                break
+
+            elif element.startswith('<') and element.endswith('>'):
+                # We have found an email.
+                # Parse it, and finalize any names from earlier
+                email.append(element[1:-1])  # Slice off the "<>"
+
+                if namebuilder:
+                    name.append(' '.join(namebuilder))
+                    namebuilder = []
+
+                # Break if we have found a second email, any other
+                # data does not fit the spec for .mailmap
+                if len(email) > 1:
+                    break
+
+            else:
+                # We have found another word in the committers name
+                namebuilder.append(element)
+
+        mailmapkey = mailmapping(
+            email=email[-1],
+            name=name[-1] if len(name) == 2 else None,
+        )
+
+        mailmap[mailmapkey] = mailmapping(
+            email=email[0],
+            name=name[0] if name else None,
+        )
+
+    return mailmap
+
+def mapname(mailmap, author):
+    """Returns the author field according to the mailmap cache, or
+    the original author field.
+
+    >>> mmdata = b"\\n".join([
+    ...     b'# Comment',
+    ...     b'Name <[e-mail]>',
+    ...     b'<[e-mail]> <[e-mail]>',
+    ...     b'Name <[e-mail]> <[e-mail]>',
+    ...     b'Name <[e-mail]> Commit <[e-mail]>',
+    ... ])
+    >>> m = parsemailmap(mmdata)
+    >>> mapname(m, b'Commit <[e-mail]>')
+    'Name <[e-mail]>'
+    >>> mapname(m, b'Name <[e-mail]>')
+    'Name <[e-mail]>'
+    >>> mapname(m, b'Commit <[e-mail]>')
+    'Name <[e-mail]>'
+    >>> mapname(m, b'Commit <[e-mail]>')
+    'Name <[e-mail]>'
+    >>> mapname(m, b'Unknown Name <[e-mail]>')
+    'Unknown Name <[e-mail]>'
+    """
+    # If the author field coming in isn't in the correct format,
+    # or the mailmap is empty just return the original author field
+    if not isauthorwellformed(author) or not mailmap:
+        return author
+
+    # Turn the user name into a mailmaptup
+    commit = mailmapping(name=person(author), email=email(author))
+
+    try:
+        # Try and use both the commit email and name as the key
+        proper = mailmap[commit]
+
+    except KeyError:
+        # If the lookup fails, use just the email as the key instead
+        # We call this commit2 as not to erase original commit fields
+        commit2 = mailmapping(email=commit.email)
+        proper = mailmap.get(commit2, mailmapping(None, None))
+
+    # Return the author field with proper values filled in
+    return '%s <%s>' % (
+        proper.name if proper.name else commit.name,
+        proper.email if proper.email else commit.email,
+    )
+
 _correctauthorformat = remod.compile(br'^[^<]+\s\<[^<>]+@[^<>]+\>$')
 
 def isauthorwellformed(author):