Merge pull request #12 from rtgdk/python3

Update tool to python3 and fix requirement differences, update REAME

.gitignore

@@ -6,6 +6,7 @@
 __pycache__/
 *.py[cod]
 *$py.class
+*.py.bak
 
 # C extensions
 *.so
@@ -127,4 +128,11 @@ dmypy.json
 # Pyre type checker
 .pyre/
 
+# IDEs
+.project
+.pydevproject
+.idea
+org.eclipse.core.resources.prefs
+.vscode
+
 # End of https://www.gitignore.io/api/python

README.md

@@ -17,10 +17,38 @@ Ensure that you are using Python3 for installation of the tool.
 
 * Install dependencies inside virtual environment
     * `pip3 install -r requirements.txt`
+
+* Install redis server on your local machine.
 
-## Usage
-First of all before using the tool you will have to create a database of SPDX license list for this just run `python build_licenses.py`.
+        **For linux users**
+        
+        * Use the command `sudo apt-get install redis-server` to install the redis server.
+
+        **For Mac users**
+
+        * Install the redis by running the command
+
+            `brew install redis`.
+        * If you want to run redis whenever your computer starts then run
+
+            `ln -sfv /usr/local/opt/redis/*.plist ~/Library/LaunchAgents`.
+
+        * To run the redis server use
+
+            `launchctl load ~/Library/LaunchAgents/homebrew.mxcl.redis.plist`.
+        * To test if the redis is working run the command `redis-cli ping`. If it returns `Pong` then you are good to go.
 
+        **For Windows users**
+
+        * Download the redis server from [here](https://github.com/microsoftarchive/redis/releases) and install it.
+    * Make sure redis server is running and keep it running until you are done using the tool.
+
+        *The redis is used to store the license text of license present on the SPDX license list. For the very first time it may take a while to build the license on the redis server.*
+
+        *SPDX License Matcher matches the license text input by the user(via license submittal form) against the data present on the redis to find for duplicate and near matches.*
+
+
+## Usage
 To run the tool just use the command `python matcher.py -f <file-name> -t <threshold>`.
 * `filename` is the file with the license text(if you don't provide the file as well then it will prompt you to add it).
 * `threshold` is a value upto which we will just won't consider a match.(optional)

requirements.txt

@@ -1,7 +1,6 @@
 redis==3.2.1
-requests==2.22.0
-jpype1==0.6.3
+requests==2.24
+jpype1==1.0.1
 jellyfish==0.6.1
 click==7.0
-python-dotenv==0.13.0
-futures; python_version == "2.7"
+python-dotenv==0.14.0

spdx_license_matcher/build_licenses.py

@@ -5,12 +5,12 @@
 from dotenv import load_dotenv
 import os
 
-from normalize import normalize
-from utils import compressStringToBytes
+from spdx_license_matcher.normalize import normalize
+from spdx_license_matcher.utils import compressStringToBytes
 
 load_dotenv()
 
-r = redis.StrictRedis(host=os.environ.get(key="SPDX_REDIS_HOST", failobj="localhost"), port=6379, db=0)
+r = redis.StrictRedis(host=os.environ.get(key="SPDX_REDIS_HOST", default="localhost"), port=6379, db=0)
 
 
 def get_url(url):

spdx_license_matcher/computation.py

@@ -1,6 +1,6 @@
-from normalize import normalize
-from sorensen_dice import get_dice_coefficient
-from utils import (checkTextStandardLicense, decompressBytesToString,
+from spdx_license_matcher.normalize import normalize
+from spdx_license_matcher.sorensen_dice import get_dice_coefficient
+from spdx_license_matcher.utils import (checkTextStandardLicense, decompressBytesToString,
                    getListedLicense)
 
 def get_close_matches(inputText, licenseData, threshold=0.9):
@@ -16,7 +16,7 @@ def get_close_matches(inputText, licenseData, threshold=0.9):
     matches = {}
     perfectMatches = {}
     normalizedInputText = normalize(inputText)
-    for key in licenseData.keys():
+    for key in list(licenseData.keys()):
         try:
             licenseName = key.decode('utf-8')
             normalizedLicenseText = decompressBytesToString(licenseData.get(key))
@@ -31,7 +31,7 @@ def get_close_matches(inputText, licenseData, threshold=0.9):
             matches[licenseName] = score
     if perfectMatches:
         return perfectMatches
-    matches = {licenseName: score for licenseName, score in matches.items() if score >= threshold}
+    matches = {licenseName: score for licenseName, score in list(matches.items()) if score >= threshold}
     return matches
 
 
@@ -49,8 +49,8 @@ def get_matching_string(matches, inputText):
         matchingString = 'There is not enough confidence threshold for the text to match against the SPDX License database.'
         return matchingString
 
-    elif all(score == 1.0 for score in matches.values()):
-        matchingString = 'The following license ID(s) match: ' + ", ".join(matches.keys())
+    elif all(score == 1.0 for score in list(matches.values())):
+        matchingString = 'The following license ID(s) match: ' + ", ".join(list(matches.keys()))
         return matchingString
 
     else:

spdx_license_matcher/matcher.py

@@ -2,10 +2,10 @@
 import codecs
 import redis
 
-from build_licenses import build_spdx_licenses, is_keys_empty,get_url
-from computation import get_close_matches, get_matching_string
-from difference import generate_diff, get_similarity_percent
-from utils import colors, get_spdx_license_text
+from spdx_license_matcher.build_licenses import build_spdx_licenses, is_keys_empty,get_url
+from spdx_license_matcher.computation import get_close_matches, get_matching_string
+from spdx_license_matcher.difference import generate_diff, get_similarity_percent
+from spdx_license_matcher.utils import colors, get_spdx_license_text
 
 from dotenv import load_dotenv
 import os
@@ -31,10 +31,10 @@ def matcher(text_file, threshold, build):
         click.echo('Building SPDX License List. This may take a while...')
         build_spdx_licenses()
 
-    r = redis.StrictRedis(host=os.environ.get(key="SPDX_REDIS_HOST", failobj="localhost"), port=6379, db=0)
-    keys = r.keys()
+    r = redis.StrictRedis(host=os.environ.get(key="SPDX_REDIS_HOST", default="localhost"), port=6379, db=0)
+    keys = list(r.keys())
     values = r.mget(keys)
-    licenseData = dict(zip(keys, values))
+    licenseData = dict(list(zip(keys, values)))
     matches = get_close_matches(inputText, licenseData, threshold)
     matchingString = get_matching_string(matches, inputText)
     if matchingString == '':

spdx_license_matcher/normalize.py

@@ -91,7 +91,7 @@ def normalize(licenseText):
     licenseText = re.sub(BULLETS_NUMBERING_REGEX, " ", licenseText)
 
     # To avoid the possibility of a non-match due to the same word being spelled differently.
-    for initial, final in VARIETAL_WORDS_SPELLING.items():
+    for initial, final in list(VARIETAL_WORDS_SPELLING.items()):
         licenseText = licenseText.replace(initial, final)
 
     # To avoid the possibility of a non-match due to different spacing of words, line breaks, or paragraphs.