Drop Python 2 for scancode-toolkit

etc/scripts/scanserv.py

@@ -45,10 +45,9 @@ def run_scan(location, **kwargs):
 
 
 if __name__ == '__channelexec__':
-    from commoncode import compat
     for kwargs in channel:  # NOQA
         # a mapping of kwargs or a location string
-        if isinstance(kwargs, (str, compat.unicode)):
+        if isinstance(kwargs, (str, str)):
             channel.send(run_scan(kwargs))  # NOQA
         elif isinstance(kwargs, dict):
             channel.send(run_scan(**kwargs))  # NOQA

etc/scripts/synclic.py

@@ -45,7 +45,6 @@
 
 from commoncode import fetch
 from commoncode import fileutils
-from commoncode import compat
 
 import licensedcode
 from licensedcode.models import load_licenses
@@ -898,7 +897,7 @@ def update_external(_attrib, _sc_val, _ext_val):
 
             continue
 
-        if (isinstance(scancode_value, compat.unicode) and isinstance(external_value, compat.unicode)):
+        if (isinstance(scancode_value, str) and isinstance(external_value, str)):
             # keep the stripped and normalized spaces value
             # normalized spaces
             normalized_scancode_value = ' '.join(scancode_value.split())

src/cluecode/finder.py

@@ -33,8 +33,6 @@
 from six import string_types
 import urlpy
 
-from commoncode import compat
-from commoncode.system import py3
 from commoncode.text import toascii
 from cluecode import finder_data
 from textcode import analysis
@@ -251,7 +249,7 @@ def find_urls(location, unique=True):
         if TRACE_URL:
             logger_debug('find_urls: lineno:', lineno, '_line:', repr(_line),
                          'type(url):', type(url), 'url:', repr(url))
-        yield compat.unicode(url), lineno
+        yield str(url), lineno
 
 
 EMPTY_URLS = set(['https', 'http', 'ftp', 'www', ])
@@ -462,7 +460,7 @@ def get_ip(s):
         return False
 
     try:
-        ip = ipaddress.ip_address(compat.unicode(s))
+        ip = ipaddress.ip_address(str(s))
         return ip
     except ValueError:
         return False

src/formattedcode/output_csv.py

@@ -33,7 +33,6 @@
 from six import string_types
 import unicodecsv
 
-from commoncode import compat
 from formattedcode import FileOptionType
 from plugincode.output import output_impl
 from plugincode.output import OutputPlugin
@@ -320,7 +319,7 @@ def flatten_package(_package, path, prefix='package__'):
                     if isinstance(component_val, list):
                         component_val = '\n'.join(component_val)
 
-                    if not isinstance(component_val, compat.unicode):
+                    if not isinstance(component_val, str):
                         component_val = repr(component_val)
 
                     existing = pack.get(component_new_key) or []
@@ -338,7 +337,7 @@ def flatten_package(_package, path, prefix='package__'):
 
         pack[nk] = ''
 
-        if isinstance(val, compat.unicode):
+        if isinstance(val, str):
             pack[nk] = val
         else:
             # Use repr if not a string

src/formattedcode/output_html.py

@@ -40,18 +40,13 @@
 import click
 import simplejson
 
-from commoncode import compat
 from commoncode.fileutils import PATH_TYPE
 from commoncode.fileutils import as_posixpath
 from commoncode.fileutils import copytree
 from commoncode.fileutils import delete
 from commoncode.fileutils import file_name
 from commoncode.fileutils import file_base_name
-from commoncode.fileutils import fsencode
 from commoncode.fileutils import parent_directory
-from commoncode.system import on_linux
-from commoncode.system import py2
-from commoncode.system import py3
 from formattedcode import FileOptionType
 from commoncode.cliutils import PluggableCommandLineOption
 from commoncode.cliutils import OUTPUT_GROUP
@@ -121,10 +116,6 @@ def is_enabled(self, custom_output, custom_template, **kwargs):
     def process_codebase(self, codebase, custom_output, custom_template, **kwargs):
         results = self.get_files(codebase, **kwargs)
         version = codebase.get_or_create_current_header().tool_version
-
-        if on_linux and py2:
-            custom_template = fsencode(custom_template)
-
         template_loc = custom_template
         output_file = custom_output
         write_templated(output_file, results, version, template_loc)
@@ -139,7 +130,7 @@ def write_templated(output_file, results, version, template_loc):
     template = get_template(template_loc)
 
     for template_chunk in generate_output(results, version, template):
-        assert isinstance(template_chunk, compat.unicode)
+        assert isinstance(template_chunk, str)
         try:
             output_file.write(template_chunk)
         except Exception:
@@ -326,16 +317,9 @@ def create_html_app(output_file, results, version, scanned_path):  # NOQA
         with io.open(join(target_assets_dir, 'help.html'), 'w', encoding='utf-8') as f:
             f.write(rendered_help)
 
-        # write json data
         # FIXME: this should a regular JSON scan format
-        if py2:
-            mode = 'wb'
-            prefix = b'data='
-        if py3:
-            mode = 'w'
-            prefix = u'data='
-        with io.open(join(target_assets_dir, 'data.js'), mode) as f:
-            f.write(prefix)
+        with io.open(join(target_assets_dir, 'data.js'), 'w') as f:
+            f.write('data=')
             simplejson.dump(results, f, iterable_as_array=True)
 
     except HtmlAppAssetCopyWarning as w:

src/formattedcode/output_json.py

@@ -30,8 +30,6 @@
 import jsonstreams
 from six import string_types
 
-from commoncode.system import py2
-from commoncode.system import py3
 from formattedcode import FileOptionType
 from commoncode.cliutils import PluggableCommandLineOption
 from commoncode.cliutils import OUTPUT_GROUP
@@ -64,27 +62,12 @@ def logger_debug(*args):
                                      and a or repr(a) for a in args))
 
 
-if py2:
-    mode = 'wb'
-    space = b' '
-    comma = b','
-    colon = b':'
-    eol = b'\n'
-
-if py3:
-    mode = 'w'
-    space = u' '
-    comma = u','
-    colon = u':'
-    eol = u'\n'
-
-
 @output_impl
 class JsonCompactOutput(OutputPlugin):
 
     options = [
         PluggableCommandLineOption(('--json', 'output_json',),
-            type=FileOptionType(mode=mode, lazy=True),
+            type=FileOptionType(mode='w', lazy=True),
             metavar='FILE',
             help='Write scan output as compact JSON to FILE.',
             help_group=OUTPUT_GROUP,
@@ -103,7 +86,7 @@ class JsonPrettyOutput(OutputPlugin):
 
     options = [
         PluggableCommandLineOption(('--json-pp', 'output_json_pp',),
-            type=FileOptionType(mode=mode, lazy=True),
+            type=FileOptionType(mode='w', lazy=True),
             metavar='FILE',
             help='Write scan output as pretty-printed JSON to FILE.',
             help_group=OUTPUT_GROUP,
@@ -134,10 +117,10 @@ def write_results(codebase, output_file, pretty=False, **kwargs):
     # If `output_file` is a path string, open the file at path `output_file` and use it as `output_file`
     close_fd = False
     if isinstance(output_file, string_types):
-        output_file = open(output_file, mode)
+        output_file = open(output_file, 'w')
         close_fd = True
 
-    # Begin writing JSON to `output_file`
+    # Begin wri'w' JSON to `output_file`
     with jsonstreams.Stream(jsonstreams.Type.object, fd=output_file, close_fd=close_fd, **jsonstreams_kwargs) as s:
         # Write headers
         codebase.add_files_count_to_current_header()
@@ -151,10 +134,8 @@ def write_results(codebase, output_file, pretty=False, **kwargs):
 
         # Write files
         codebase_files = OutputPlugin.get_files(codebase, **kwargs)
-        if py3:
-            # OutputPlugin.get_files() returns a `map()`, which isn's JSON
-            # serializable in Python 3
-            codebase_files = list(codebase_files)
+        # OutputPlugin.get_files() returns a generator, not JSON-serializable
+        codebase_files = list(codebase_files)
         s.write('files', codebase_files)
 
 

src/formattedcode/output_jsonlines.py

@@ -29,8 +29,6 @@
 
 import simplejson
 
-from commoncode.system import py2
-from commoncode.system import py3
 from formattedcode import FileOptionType
 from commoncode.cliutils import OUTPUT_GROUP
 from commoncode.cliutils import PluggableCommandLineOption
@@ -42,29 +40,12 @@
 """
 
 
-if py2:
-    mode = 'wb'
-    space = b' '
-    comma = b','
-    colon = b':'
-    eol = b'\n'
-    file_key = b'files'
-
-if py3:
-    mode = 'w'
-    space = u' '
-    comma = u','
-    colon = u':'
-    eol = u'\n'
-    file_key = u'files'
-
-
 @output_impl
 class JsonLinesOutput(OutputPlugin):
 
     options = [
         PluggableCommandLineOption(('--json-lines', 'output_json_lines',),
-            type=FileOptionType(mode=mode, lazy=True),
+            type=FileOptionType(mode='w', lazy=True),
             metavar='FILE',
             help='Write scan output as JSON Lines to FILE.',
             help_group=OUTPUT_GROUP,
@@ -86,21 +67,21 @@ def process_codebase(self, codebase, output_json_lines, **kwargs):
         simplejson_kwargs = dict(
             iterable_as_array=True,
             encoding='utf-8',
-            separators=(comma, colon,)
+            separators=(u',', u':',)
         )
         output_json_lines.write(
             simplejson.dumps(headers, **simplejson_kwargs))
-        output_json_lines.write(eol)
+        output_json_lines.write('\n')
 
         for name, value in codebase.attributes.to_dict().items():
             if value:
                 smry = {name: value}
                 output_json_lines.write(
                     simplejson.dumps(smry, **simplejson_kwargs))
-                output_json_lines.write(eol)
+                output_json_lines.write('\n')
 
         for scanned_file in files:
-            scanned_file_line = {file_key: [scanned_file]}
+            scanned_file_line = {'files': [scanned_file]}
             output_json_lines.write(
                 simplejson.dumps(scanned_file_line, **simplejson_kwargs))
-            output_json_lines.write(eol)
+            output_json_lines.write('\n')

src/formattedcode/output_spdx.py

@@ -196,8 +196,8 @@ def write_spdx(output_file, files, tool_name, tool_version, notice, input_file,
     """
     Write scan output as SPDX Tag/value or RDF.
     """
+    as_rdf = not as_tagvalue
     _patch_license_list()
-
     absinput = abspath(input_file)
 
     if isdir(absinput):
@@ -341,24 +341,20 @@ def write_spdx(output_file, files, tool_name, tool_version, notice, input_file,
 
         if as_tagvalue:
             from spdx.writers.tagvalue import write_document  # NOQA
-        else:
+        elif as_rdf:
             from spdx.writers.rdf import write_document  # NOQA
 
         if as_tagvalue:
-            # unicode text everywhere
             spdx_output = StringIO()
-        else:
-            # rdf as utf-encoded bytes on Py2
+        elif as_rdf:
+            # rdf is utf-encoded bytes
             spdx_output = BytesIO()
 
         write_document(doc, spdx_output, validate=False)
         result = spdx_output.getvalue()
 
-        if as_tagvalue:
-            # unicode text everywhere
-            pass
-        else:
-            # rdf as utf-encoded bytes on Py2
+        if as_rdf:
+            # rdf is utf-encoded bytes
             result = result.decode('utf-8')
 
         output_file.write(result)

src/licensedcode/cache.py

@@ -38,7 +38,6 @@
 from commoncode.fileutils import resource_iter
 from commoncode.fileutils import create_dir
 from commoncode import ignore
-from commoncode.system import py3
 
 from scancode_config import scancode_cache_dir
 from scancode_config import scancode_src_dir
@@ -285,10 +284,7 @@ def load_index(cache_file, use_loads=False):
                 'Please delete "{cache_file}" and retry.\n'
                 'If the problem persists, copy this error message '
                 'and submit a bug report.\n'.format(**locals()))
-            if py3:
-                raise ex_type(message).with_traceback(ex_traceback)
-            else:
-                six.reraise(ex_type, message, ex_traceback)
+            raise ex_type(message).with_traceback(ex_traceback)
 
 
 _ignored_from_hash = partial(
@@ -314,8 +310,7 @@ def tree_checksum(tree_base_dir=scancode_src_dir, _ignored=_ignored_from_hash):
     resources = resource_iter(tree_base_dir, ignored=_ignored, with_dirs=False)
     hashable = (pth + str(getmtime(pth)) + str(getsize(pth)) for pth in resources)
     hashable = ''.join(sorted(hashable))
-    if py3:
-        hashable=hashable.encode('utf-8')
+    hashable=hashable.encode('utf-8')
     return md5(hashable).hexdigest()
 
 

src/licensedcode/data/licenses/ecfonts-1.0.yml

@@ -3,5 +3,6 @@ short_name: latex-ec-fonts
 name: Copyright notice to the ec fonts
 category: Permissive
 homepage_url: http://dante.ctan.org
+owner: Joerg Knappen
 text_urls:
     - http://dante.ctan.org/tex-archive/fonts/ec/src/copyrite.txt

src/licensedcode/index.py

@@ -41,12 +41,6 @@
 import sys
 from time import time
 
-# Python 2 and 3 support
-try:
-    import itertools.izip as zip  # NOQA
-except ImportError:
-    pass
-
 from intbitset import intbitset
 from six import string_types
 

src/licensedcode/match_hash.py

@@ -29,8 +29,6 @@
 
 from six import string_types
 
-from commoncode.system import py2
-from commoncode.system import py3
 from licensedcode.match import LicenseMatch
 from licensedcode.spans import Span
 
@@ -65,10 +63,7 @@ def tokens_hash(tokens):
     """
     Return a digest binary string computed from a sequence of numeric token ids.
     """
-    if py2:
-        as_bytes = array('h', tokens).tostring()
-    if py3:
-        as_bytes = array('h', tokens).tobytes()
+    as_bytes = array('h', tokens).tobytes()
     return md5(as_bytes).digest()