Add requirement_parser into trains-agent instead as a dependency. Fix requirement_parser to support 'package @ git+http' lines

requirements.txt

@@ -13,7 +13,6 @@ pyjwt>=1.6.4
 PyYAML>=3.12
 requests-file>=1.4.2
 requests>=2.20.0
-requirements_parser>=0.2.0
 six>=1.11.0
 tqdm>=4.19.5
 typing>=3.6.4

trains_agent/external/requirements_parser/__init__.py

@@ -0,0 +1,22 @@
+from .parser import parse   # noqa
+
+_MAJOR = 0
+_MINOR = 2
+_PATCH = 0
+
+
+def version_tuple():
+    '''
+    Returns a 3-tuple of ints that represent the version
+    '''
+    return (_MAJOR, _MINOR, _PATCH)
+
+
+def version():
+    '''
+    Returns a string representation of the version
+    '''
+    return '%d.%d.%d' % (version_tuple())
+
+
+__version__ = version()

trains_agent/external/requirements_parser/fragment.py

@@ -0,0 +1,44 @@
+import re
+
+# Copied from pip
+# https://github.com/pypa/pip/blob/281eb61b09d87765d7c2b92f6982b3fe76ccb0af/pip/index.py#L947
+HASH_ALGORITHMS = set(['sha1', 'sha224', 'sha384', 'sha256', 'sha512', 'md5'])
+
+extras_require_search = re.compile(
+    r'(?P<name>.+)\[(?P<extras>[^\]]+)\]').search
+
+
+def parse_fragment(fragment_string):
+    """Takes a fragment string nd returns a dict of the components"""
+    fragment_string = fragment_string.lstrip('#')
+
+    try:
+        return dict(
+            key_value_string.split('=')
+            for key_value_string in fragment_string.split('&')
+        )
+    except ValueError:
+        raise ValueError(
+            'Invalid fragment string {fragment_string}'.format(
+                fragment_string=fragment_string
+            )
+        )
+
+
+def get_hash_info(d):
+    """Returns the first matching hashlib name and value from a dict"""
+    for key in d.keys():
+        if key.lower() in HASH_ALGORITHMS:
+            return key, d[key]
+
+    return None, None
+
+
+def parse_extras_require(egg):
+    if egg is not None:
+        match = extras_require_search(egg)
+        if match is not None:
+            name = match.group('name')
+            extras = match.group('extras')
+            return name, [extra.strip() for extra in extras.split(',')]
+    return egg, []

trains_agent/external/requirements_parser/parser.py

@@ -0,0 +1,50 @@
+import os
+import warnings
+
+from .requirement import Requirement
+
+
+def parse(reqstr):
+    """
+    Parse a requirements file into a list of Requirements
+
+    See: pip/req.py:parse_requirements()
+
+    :param reqstr: a string or file like object containing requirements
+    :returns: a *generator* of Requirement objects
+    """
+    filename = getattr(reqstr, 'name', None)
+    try:
+        # Python 2.x compatibility
+        if not isinstance(reqstr, basestring):
+            reqstr = reqstr.read()
+    except NameError:
+        # Python 3.x only
+        if not isinstance(reqstr, str):
+            reqstr = reqstr.read()
+
+    for line in reqstr.splitlines():
+        line = line.strip()
+        if line == '':
+            continue
+        elif not line or line.startswith('#'):
+            # comments are lines that start with # only
+            continue
+        elif line.startswith('-r') or line.startswith('--requirement'):
+            _, new_filename = line.split()
+            new_file_path = os.path.join(os.path.dirname(filename or '.'),
+                                         new_filename)
+            with open(new_file_path) as f:
+                for requirement in parse(f):
+                    yield requirement
+        elif line.startswith('-f') or line.startswith('--find-links') or \
+                line.startswith('-i') or line.startswith('--index-url') or \
+                line.startswith('--extra-index-url') or \
+                line.startswith('--no-index'):
+            warnings.warn('Private repos not supported. Skipping.')
+            continue
+        elif line.startswith('-Z') or line.startswith('--always-unzip'):
+            warnings.warn('Unused option --always-unzip. Skipping.')
+            continue
+        else:
+            yield Requirement.parse(line)

trains_agent/external/requirements_parser/requirement.py

@@ -0,0 +1,236 @@
+from __future__ import unicode_literals
+import re
+from pkg_resources import Requirement as Req
+
+from .fragment import get_hash_info, parse_fragment, parse_extras_require
+from .vcs import VCS, VCS_SCHEMES
+
+
+URI_REGEX = re.compile(
+    r'^(?P<scheme>https?|file|ftps?)://(?P<path>[^#]+)'
+    r'(#(?P<fragment>\S+))?'
+)
+
+VCS_REGEX = re.compile(
+    r'^(?P<scheme>{0})://'.format(r'|'.join(
+        [scheme.replace('+', r'\+') for scheme in VCS_SCHEMES])) +
+    r'((?P<login>[^/@]+)@)?'
+    r'(?P<path>[^#@]+)'
+    r'(@(?P<revision>[^#]+))?'
+    r'(#(?P<fragment>\S+))?'
+)
+
+# This matches just about everyting
+LOCAL_REGEX = re.compile(
+    r'^((?P<scheme>file)://)?'
+    r'(?P<path>[^#]+)' +
+    r'(#(?P<fragment>\S+))?'
+)
+
+
+class Requirement(object):
+    """
+    Represents a single requirementfrom trains_agent.external.requirements_parser.requirement import Requirement
+
+    Typically instances of this class are created with ``Requirement.parse``.
+    For local file requirements, there's no verification that the file
+    exists. This class attempts to be *dict-like*.
+
+    See: http://www.pip-installer.org/en/latest/logic.html
+
+    **Members**:
+
+    * ``line`` - the actual requirement line being parsed
+    * ``editable`` - a boolean whether this requirement is "editable"
+    * ``local_file`` - a boolean whether this requirement is a local file/path
+    * ``specifier`` - a boolean whether this requirement used a requirement
+      specifier (eg. "django>=1.5" or "requirements")
+    * ``vcs`` - a string specifying the version control system
+    * ``revision`` - a version control system specifier
+    * ``name`` - the name of the requirement
+    * ``uri`` - the URI if this requirement was specified by URI
+    * ``subdirectory`` - the subdirectory fragment of the URI
+    * ``path`` - the local path to the requirement
+    * ``hash_name`` - the type of hashing algorithm indicated in the line
+    * ``hash`` - the hash value indicated by the requirement line
+    * ``extras`` - a list of extras for this requirement
+      (eg. "mymodule[extra1, extra2]")
+    * ``specs`` - a list of specs for this requirement
+      (eg. "mymodule>1.5,<1.6" => [('>', '1.5'), ('<', '1.6')])
+    """
+
+    def __init__(self, line):
+        # Do not call this private method
+        self.line = line
+        self.editable = False
+        self.local_file = False
+        self.specifier = False
+        self.vcs = None
+        self.name = None
+        self.subdirectory = None
+        self.uri = None
+        self.path = None
+        self.revision = None
+        self.hash_name = None
+        self.hash = None
+        self.extras = []
+        self.specs = []
+
+    def __repr__(self):
+        return '<Requirement: "{0}">'.format(self.line)
+
+    def __getitem__(self, key):
+        return getattr(self, key)
+
+    def keys(self):
+        return self.__dict__.keys()
+
+    @classmethod
+    def parse_editable(cls, line):
+        """
+        Parses a Requirement from an "editable" requirement which is either
+        a local project path or a VCS project URI.
+
+        See: pip/req.py:from_editable()
+
+        :param line: an "editable" requirement
+        :returns: a Requirement instance for the given line
+        :raises: ValueError on an invalid requirement
+        """
+
+        req = cls('-e {0}'.format(line))
+        req.editable = True
+        vcs_match = VCS_REGEX.match(line)
+        local_match = LOCAL_REGEX.match(line)
+
+        if vcs_match is not None:
+            groups = vcs_match.groupdict()
+            if groups.get('login'):
+                req.uri = '{scheme}://{login}@{path}'.format(**groups)
+            else:
+                req.uri = '{scheme}://{path}'.format(**groups)
+            req.revision = groups['revision']
+            if groups['fragment']:
+                fragment = parse_fragment(groups['fragment'])
+                egg = fragment.get('egg')
+                req.name, req.extras = parse_extras_require(egg)
+                req.hash_name, req.hash = get_hash_info(fragment)
+                req.subdirectory = fragment.get('subdirectory')
+            for vcs in VCS:
+                if req.uri.startswith(vcs):
+                    req.vcs = vcs
+        else:
+            assert local_match is not None, 'This should match everything'
+            groups = local_match.groupdict()
+            req.local_file = True
+            if groups['fragment']:
+                fragment = parse_fragment(groups['fragment'])
+                egg = fragment.get('egg')
+                req.name, req.extras = parse_extras_require(egg)
+                req.hash_name, req.hash = get_hash_info(fragment)
+                req.subdirectory = fragment.get('subdirectory')
+            req.path = groups['path']
+
+        return req
+
+    @classmethod
+    def parse_line(cls, line):
+        """
+        Parses a Requirement from a non-editable requirement.
+
+        See: pip/req.py:from_line()
+
+        :param line: a "non-editable" requirement
+        :returns: a Requirement instance for the given line
+        :raises: ValueError on an invalid requirement
+        """
+
+        req = cls(line)
+
+        vcs_match = VCS_REGEX.match(line)
+        uri_match = URI_REGEX.match(line)
+        local_match = LOCAL_REGEX.match(line)
+
+        if vcs_match is not None:
+            groups = vcs_match.groupdict()
+            if groups.get('login'):
+                req.uri = '{scheme}://{login}@{path}'.format(**groups)
+            else:
+                req.uri = '{scheme}://{path}'.format(**groups)
+            req.revision = groups['revision']
+            if groups['fragment']:
+                fragment = parse_fragment(groups['fragment'])
+                egg = fragment.get('egg')
+                req.name, req.extras = parse_extras_require(egg)
+                req.hash_name, req.hash = get_hash_info(fragment)
+                req.subdirectory = fragment.get('subdirectory')
+            for vcs in VCS:
+                if req.uri.startswith(vcs):
+                    req.vcs = vcs
+        elif uri_match is not None:
+            groups = uri_match.groupdict()
+            req.uri = '{scheme}://{path}'.format(**groups)
+            if groups['fragment']:
+                fragment = parse_fragment(groups['fragment'])
+                egg = fragment.get('egg')
+                req.name, req.extras = parse_extras_require(egg)
+                req.hash_name, req.hash = get_hash_info(fragment)
+                req.subdirectory = fragment.get('subdirectory')
+            if groups['scheme'] == 'file':
+                req.local_file = True
+        elif '#egg=' in line:
+            # Assume a local file match
+            assert local_match is not None, 'This should match everything'
+            groups = local_match.groupdict()
+            req.local_file = True
+            if groups['fragment']:
+                fragment = parse_fragment(groups['fragment'])
+                egg = fragment.get('egg')
+                name, extras = parse_extras_require(egg)
+                req.name = fragment.get('egg')
+                req.hash_name, req.hash = get_hash_info(fragment)
+                req.subdirectory = fragment.get('subdirectory')
+            req.path = groups['path']
+        else:
+            # This is a requirement specifier.
+            # Delegate to pkg_resources and hope for the best
+            req.specifier = True
+            pkg_req = Req.parse(line)
+            req.name = pkg_req.unsafe_name
+            req.extras = list(pkg_req.extras)
+            req.specs = pkg_req.specs
+        return req
+
+    @classmethod
+    def parse(cls, line):
+        """
+        Parses a Requirement from a line of a requirement file.
+
+        :param line: a line of a requirement file
+        :returns: a Requirement instance for the given line
+        :raises: ValueError on an invalid requirement
+        """
+        line = line.lstrip()
+        if line.startswith('-e') or line.startswith('--editable'):
+            # Editable installs are either a local project path
+            # or a VCS project URI
+            return cls.parse_editable(
+                re.sub(r'^(-e|--editable=?)\s*', '', line))
+        elif '@' in line:
+            # Allegro bug fix: support 'name @ git+' entries
+            name, vcs = line.split('@', 1)
+            name = name.strip()
+            vcs = vcs.strip()
+            # noinspection PyBroadException
+            try:
+                # check if the name is valid & parsed
+                Req.parse(name)
+                # if we are here, name is a valid package name, check if the vcs part is valid
+                if VCS_REGEX.match(vcs):
+                    req = cls.parse_line(vcs)
+                    req.name = name
+                    return req
+            except Exception:
+                pass
+
+        return cls.parse_line(line)

trains_agent/external/requirements_parser/vcs.py

@@ -0,0 +1,30 @@
+from __future__ import unicode_literals
+
+VCS = [
+    'git',
+    'hg',
+    'svn',
+    'bzr',
+]
+
+VCS_SCHEMES = [
+    'git',
+    'git+https',
+    'git+ssh',
+    'git+git',
+    'hg+http',
+    'hg+https',
+    'hg+static-http',
+    'hg+ssh',
+    'svn',
+    'svn+svn',
+    'svn+http',
+    'svn+https',
+    'svn+ssh',
+    'bzr+http',
+    'bzr+https',
+    'bzr+ssh',
+    'bzr+sftp',
+    'bzr+ftp',
+    'bzr+lp',
+]

trains_agent/helper/package/conda_api.py

@@ -14,8 +14,8 @@ import yaml
 from time import time
 from attr import attrs, attrib, Factory
 from pathlib2 import Path
-from requirements import parse
+from trains_agent.external.requirements_parser import parse
-from requirements.requirement import Requirement
+from trains_agent.external.requirements_parser.requirement import Requirement
 
 from trains_agent.errors import CommandFailedError
 from trains_agent.helper.base import rm_tree, NonStrictAttrs, select_for_platform, is_windows_platform

trains_agent/helper/package/requirements.py

@@ -12,15 +12,15 @@ from typing import Text, List, Type, Optional, Tuple, Dict
 
 from pathlib2 import Path
 from pyhocon import ConfigTree
-from requirements import parse
-# noinspection PyPackageRequirements
-from requirements.requirement import Requirement
 
 import six
 from trains_agent.definitions import PIP_EXTRA_INDICES
 from trains_agent.helper.base import warning, is_conda, which, join_lines, is_windows_platform
 from trains_agent.helper.process import Argv, PathLike
 from trains_agent.session import Session, normalize_cuda_version
+from trains_agent.external.requirements_parser import parse
+from trains_agent.external.requirements_parser.requirement import Requirement
+
 from .translator import RequirementsTranslator
 
 
@@ -57,7 +57,7 @@ class MarkerRequirement(object):
         elif self.vcs:
             # leave the line as is, let pip handle it
             if self.line:
-                parts = [self.line]
+                return self.line
             else:
                 # let's build the line manually
                 parts = [