nebulento 0.0.1__tar.gz

nebulento-0.0.1/LICENSE.md

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

nebulento-0.0.1/PKG-INFO

@@ -0,0 +1,89 @@
+Metadata-Version: 2.1
+Name: nebulento
+Version: 0.0.1
+Summary: dead simple fuzzy matching intent parser
+Home-page: https://github.com/OpenJarbas/nebulento
+Author: jarbasai
+Author-email: jarbasai@mailfence.com
+License: apache-2.0
+Description: # Nebulento
+        
+        *A lightweight, dead simple fuzzy matching intent parser*
+        
+        Built on top of [rapidfuzz](https://github.com/maxbachmann/rapidfuzz)
+        
+        Finds the closest matching intent via fuzzy match between the text and all of the training sentences you provided. Works best when you have a small number of sentences (dozens to hundreds) and need some resiliency to spelling errors (i.e., from text chat).
+        
+        ## Usage
+        
+        ```python
+        from nebulento import IntentContainer, MatchStrategy
+        
+        container = IntentContainer(fuzzy_strategy=MatchStrategy.TOKEN_SET_RATIO)
+        
+        container.add_intent('hello', [
+            'hello', 'hi', 'how are you', "what's up"
+        ])
+        container.add_intent('buy', [
+            'buy {item}', 'purchase {item}', 'get {item}', 'get {item} for me'
+        ])
+        container.add_entity('item', [
+            'milk', 'cheese'
+        ])
+        
+        container.calc_intent('hello')
+        # {'best_match': 'hello',
+        #  'conf': 1.0,
+        #  'entities': {},
+        #  'match_strategy': 'TOKEN_SET_RATIO',
+        #  'name': 'hello',
+        #  'utterance': 'hello',
+        #  'utterance_consumed': 'hello',
+        #  'utterance_remainder': ''}
+                                 
+        container.calc_intent('buy milk')
+        # {'best_match': 'buy {item}',
+        #  'conf': 0.71875,
+        #  'entities': {'item': ['milk']},
+        #  'match_strategy': 'TOKEN_SET_RATIO',
+        #  'name': 'buy',
+        #  'utterance': 'buy milk',
+        #  'utterance_consumed': 'buy milk',
+        #  'utterance_remainder': ''}
+        
+        
+        container.add_intent('look_at_thing', ['I see {thing} (in|on) {place}'])
+        container.add_entity("place", ["floor", "table"])
+        
+        container.calc_intent('I see trash in the floor')
+        #{'best_match': 'i see {thing} in {place}',
+        # 'conf': 0.65625,
+        # 'entities': {'place': ['floor']},
+        # 'match_strategy': 'TOKEN_SET_RATIO',
+        # 'name': 'look_at_thing',
+        # 'utterance': 'i see trash in the floor',
+        # 'utterance_consumed': 'i see in floor',
+        # 'utterance_remainder': 'trash the'}
+                    
+        container.add_entity("thing", ["food"])
+        container.calc_intent('I see food in the table')
+        #{'best_match': 'i see {thing} in {place}',
+        # 'conf': 0.7007978723404256,
+        # 'entities': {'place': ['table'], 'thing': ['food']},
+        # 'match_strategy': 'TOKEN_SET_RATIO',
+        # 'name': 'look_at_thing',
+        # 'utterance': 'i see food in the table',
+        # 'utterance_consumed': 'i see in table food',
+        # 'utterance_remainder': 'the'}
+        
+        ```
+        
+        ## Match Strategies
+        
+        - **Ratio**: Use `MatchStrategy.RATIO` when you need to compare strings and determine their overall similarity. It is effective for handling cases where strings have minor differences due to typos or spelling variations.
+        - **Partial Ratio**: `MatchStrategy.PARTIAL_RATIO` is useful when you want to focus on the best matching substring between two strings. It handles cases where one string is a subset or prefix of the other, providing a more targeted similarity measure.
+        - **Token Set Ratio**: `MatchStrategy.TOKEN_SET_RATIO` is ideal when you want to compare strings without considering their word order. It captures the essence of the strings’ content, making it suitable for scenarios where word arrangement might vary but the overall content remains similar.
+        - **Token Sort Ratio**: Use `MatchStrategy.TOKEN_SORT_RATIO` when you want to compare strings and consider word order variations. It is particularly effective when the words are expected to be similar, but their arrangement may differ.
+        
+Platform: UNKNOWN
+Description-Content-Type: text/markdown

nebulento-0.0.1/README.md

@@ -0,0 +1,78 @@
+# Nebulento
+
+*A lightweight, dead simple fuzzy matching intent parser*
+
+Built on top of [rapidfuzz](https://github.com/maxbachmann/rapidfuzz)
+
+Finds the closest matching intent via fuzzy match between the text and all of the training sentences you provided. Works best when you have a small number of sentences (dozens to hundreds) and need some resiliency to spelling errors (i.e., from text chat).
+
+## Usage
+
+```python
+from nebulento import IntentContainer, MatchStrategy
+
+container = IntentContainer(fuzzy_strategy=MatchStrategy.TOKEN_SET_RATIO)
+
+container.add_intent('hello', [
+    'hello', 'hi', 'how are you', "what's up"
+])
+container.add_intent('buy', [
+    'buy {item}', 'purchase {item}', 'get {item}', 'get {item} for me'
+])
+container.add_entity('item', [
+    'milk', 'cheese'
+])
+
+container.calc_intent('hello')
+# {'best_match': 'hello',
+#  'conf': 1.0,
+#  'entities': {},
+#  'match_strategy': 'TOKEN_SET_RATIO',
+#  'name': 'hello',
+#  'utterance': 'hello',
+#  'utterance_consumed': 'hello',
+#  'utterance_remainder': ''}
+                         
+container.calc_intent('buy milk')
+# {'best_match': 'buy {item}',
+#  'conf': 0.71875,
+#  'entities': {'item': ['milk']},
+#  'match_strategy': 'TOKEN_SET_RATIO',
+#  'name': 'buy',
+#  'utterance': 'buy milk',
+#  'utterance_consumed': 'buy milk',
+#  'utterance_remainder': ''}
+
+
+container.add_intent('look_at_thing', ['I see {thing} (in|on) {place}'])
+container.add_entity("place", ["floor", "table"])
+
+container.calc_intent('I see trash in the floor')
+#{'best_match': 'i see {thing} in {place}',
+# 'conf': 0.65625,
+# 'entities': {'place': ['floor']},
+# 'match_strategy': 'TOKEN_SET_RATIO',
+# 'name': 'look_at_thing',
+# 'utterance': 'i see trash in the floor',
+# 'utterance_consumed': 'i see in floor',
+# 'utterance_remainder': 'trash the'}
+            
+container.add_entity("thing", ["food"])
+container.calc_intent('I see food in the table')
+#{'best_match': 'i see {thing} in {place}',
+# 'conf': 0.7007978723404256,
+# 'entities': {'place': ['table'], 'thing': ['food']},
+# 'match_strategy': 'TOKEN_SET_RATIO',
+# 'name': 'look_at_thing',
+# 'utterance': 'i see food in the table',
+# 'utterance_consumed': 'i see in table food',
+# 'utterance_remainder': 'the'}
+
+```
+
+## Match Strategies
+
+- **Ratio**: Use `MatchStrategy.RATIO` when you need to compare strings and determine their overall similarity. It is effective for handling cases where strings have minor differences due to typos or spelling variations.
+- **Partial Ratio**: `MatchStrategy.PARTIAL_RATIO` is useful when you want to focus on the best matching substring between two strings. It handles cases where one string is a subset or prefix of the other, providing a more targeted similarity measure.
+- **Token Set Ratio**: `MatchStrategy.TOKEN_SET_RATIO` is ideal when you want to compare strings without considering their word order. It captures the essence of the strings’ content, making it suitable for scenarios where word arrangement might vary but the overall content remains similar.
+- **Token Sort Ratio**: Use `MatchStrategy.TOKEN_SORT_RATIO` when you want to compare strings and consider word order variations. It is particularly effective when the words are expected to be similar, but their arrangement may differ.

nebulento-0.0.1/nebulento/__init__.py

@@ -0,0 +1,97 @@
+import logging
+from nebulento.fuzz import MatchStrategy, match_one
+from nebulento.bracket_expansion import expand_template, expand_slots
+import quebra_frases
+
+LOG = logging.getLogger('nebulento')
+
+
+class IntentContainer:
+    def __init__(self, fuzzy_strategy=MatchStrategy.DAMERAU_LEVENSHTEIN_SIMILARITY,
+                 ignore_case=True):
+        self.fuzzy_strategy = fuzzy_strategy
+        self.ignore_case = ignore_case
+        self.registered_intents = {}
+        self.registered_entities = {}
+
+    def match_entities(self, sentence):
+        if self.ignore_case:
+            sentence = sentence.lower()
+        matches = {}
+        for entity, samples in self.registered_entities.items():
+            chunked = quebra_frases.chunk(sentence, samples)
+            matches[entity] = [s for s in samples if s in chunked]
+        return matches
+
+    def match_fuzzy(self, sentence):
+        if self.ignore_case:
+            sentence = sentence.lower()
+        entities = self.match_entities(sentence)
+        for intent, samples in self.registered_intents.items():
+            samples = self.registered_intents[intent]
+
+            sent, score = match_one(sentence, samples,
+                                    strategy=self.fuzzy_strategy)
+            remainder = [
+                w for w in quebra_frases.word_tokenize(sentence)
+                if w not in quebra_frases.word_tokenize(sent)]
+            consumed = [
+                w for w in quebra_frases.word_tokenize(sentence)
+                if w in quebra_frases.word_tokenize(sent)]
+
+            tagged_entities = {}
+            for ent, v in entities.items():
+                if v and any("{" + ent + "}" in s for s in samples):
+                    score = 0.25 + score * 0.75
+                    tagged_entities[ent] = v
+                    consumed += [_ for _ in v if _ not in consumed]
+                    remainder = [_ for _ in remainder if _ not in v]
+            remainder = " ".join(remainder)
+            consumed = " ".join(consumed)
+            yield {"best_match": sent,
+                   "conf": min(score, 1),
+                   "entities": tagged_entities,
+                   "match_strategy": self.fuzzy_strategy.name,
+                   "utterance": sentence,
+                   "utterance_remainder": remainder,
+                   "utterance_consumed": consumed,
+                   "name": intent}
+
+    def add_intent(self, name, lines):
+        expanded = []
+        for l in lines:
+            expanded += expand_template(l)
+        if self.ignore_case:
+            expanded = [l.lower() for l in expanded]
+        self.registered_intents[name] = expanded
+
+    def remove_intent(self, name):
+        if name in self.registered_intents:
+            del self.registered_intents[name]
+
+    def add_entity(self, name, lines):
+        expanded = []
+        for l in lines:
+            expanded += expand_template(l)
+        if self.ignore_case:
+            expanded = [l.lower() for l in expanded]
+        self.registered_entities[name] = expanded
+
+    def remove_entity(self, name):
+        if name in self.registered_entities:
+            del self.registered_entities[name]
+
+    def calc_intents(self, query):
+        for intent in self.match_fuzzy(query):
+            yield intent
+
+    def calc_intent(self, query):
+        return max(
+            self.calc_intents(query),
+            key=lambda x: x["conf"],
+            default={"best_match": None,
+                     "conf": 0,
+                     "match_strategy": self.fuzzy_strategy,
+                     "utterance": query,
+                     "name": None}
+        )

nebulento-0.0.1/nebulento/bracket_expansion.py

@@ -0,0 +1,72 @@
+import itertools
+import re
+from typing import List, Dict
+
+
+def expand_template(template: str) -> List[str]:
+    def expand_optional(text):
+        """Replace [optional] with two options: one with and one without."""
+        return re.sub(r"\[([^\[\]]+)\]", lambda m: f"({m.group(1)}|)", text)
+
+    def expand_alternatives(text):
+        """Expand (alternative|choices) into a list of choices."""
+        parts = []
+        for segment in re.split(r"(\([^\(\)]+\))", text):
+            if segment.startswith("(") and segment.endswith(")"):
+                options = segment[1:-1].split("|")
+                parts.append(options)
+            else:
+                parts.append([segment])
+        return itertools.product(*parts)
+
+    def fully_expand(texts):
+        """Iteratively expand alternatives until all possibilities are covered."""
+        result = set(texts)
+        while True:
+            expanded = set()
+            for text in result:
+                options = list(expand_alternatives(text))
+                expanded.update(["".join(option).strip() for option in options])
+            if expanded == result:  # No new expansions found
+                break
+            result = expanded
+        return sorted(result)  # Return a sorted list for consistency
+
+    # Expand optional items first
+    template = expand_optional(template)
+
+    # Fully expand all combinations of alternatives
+    return fully_expand([template])
+
+
+def expand_slots(template: str, slots: Dict[str, List[str]]) -> List[str]:
+    """Expand a template by first expanding alternatives and optional components,
+    then substituting slot placeholders with their corresponding options.
+
+    Args:
+        template (str): The input string template to expand.
+        slots (dict): A dictionary where keys are slot names and values are lists of possible replacements.
+
+    Returns:
+        list[str]: A list of all expanded combinations.
+    """
+    # Expand alternatives and optional components
+    base_expansions = expand_template(template)
+
+    # Process slots
+    all_sentences = []
+    for sentence in base_expansions:
+        matches = re.findall(r"\{([^\{\}]+)\}", sentence)
+        if matches:
+            # Create all combinations for slots in the sentence
+            slot_options = [slots.get(match, [f"{{{match}}}"]) for match in matches]
+            for combination in itertools.product(*slot_options):
+                filled_sentence = sentence
+                for slot, replacement in zip(matches, combination):
+                    filled_sentence = filled_sentence.replace(f"{{{slot}}}", replacement)
+                all_sentences.append(filled_sentence)
+        else:
+            # No slots to expand
+            all_sentences.append(sentence)
+
+    return all_sentences

nebulento-0.0.1/nebulento/fuzz.py

@@ -0,0 +1,88 @@
+import logging
+from difflib import SequenceMatcher
+from enum import IntEnum, auto
+
+import rapidfuzz
+
+LOG = logging.getLogger('nebulento')
+
+
+class MatchStrategy(IntEnum):
+    SIMPLE_RATIO = auto()
+    RATIO = auto()
+    PARTIAL_RATIO = auto()
+    TOKEN_SORT_RATIO = auto()
+    TOKEN_SET_RATIO = auto()
+    PARTIAL_TOKEN_RATIO = auto()
+    PARTIAL_TOKEN_SORT_RATIO = auto()
+    PARTIAL_TOKEN_SET_RATIO = auto()
+    DAMERAU_LEVENSHTEIN_SIMILARITY = auto()
+
+
+def fuzzy_match(x, against, strategy=MatchStrategy.SIMPLE_RATIO):
+    """Perform a 'fuzzy' comparison between two strings.
+    Returns:
+        float: match percentage -- 1.0 for perfect match,
+               down to 0.0 for no match at all.
+    """
+    if strategy == MatchStrategy.RATIO:
+        score = rapidfuzz.fuzz.ratio(x, against) / 100
+    elif strategy == MatchStrategy.PARTIAL_RATIO:
+        score = rapidfuzz.fuzz.partial_ratio(x, against) / 100
+    elif strategy == MatchStrategy.TOKEN_SORT_RATIO:
+        score = rapidfuzz.fuzz.token_sort_ratio(x, against) / 100
+    elif strategy == MatchStrategy.TOKEN_SET_RATIO:
+        score = rapidfuzz.fuzz.token_set_ratio(x, against) / 100
+    elif strategy == MatchStrategy.PARTIAL_TOKEN_SORT_RATIO:
+        score = rapidfuzz.fuzz.partial_token_sort_ratio(x, against) / 100
+    elif strategy == MatchStrategy.PARTIAL_TOKEN_SET_RATIO:
+        score = rapidfuzz.fuzz.partial_token_set_ratio(x, against) / 100
+    elif strategy == MatchStrategy.PARTIAL_TOKEN_RATIO:
+        score = rapidfuzz.fuzz.partial_token_ratio(x, against) / 100
+    elif strategy == MatchStrategy.DAMERAU_LEVENSHTEIN_SIMILARITY:
+        score = rapidfuzz.distance.DamerauLevenshtein.normalized_similarity(x, against)
+    else:
+        score = SequenceMatcher(None, x, against).ratio()
+
+    return score
+
+
+def match_one(query, choices, match_func=None,
+              strategy=MatchStrategy.DAMERAU_LEVENSHTEIN_SIMILARITY):
+    """
+        Find best match from a list or dictionary given an input
+
+        Arguments:
+            query:   string to test
+            choices: list or dictionary of choices
+
+        Returns: tuple with best match, score
+    """
+    return match_all(query, choices, match_func, strategy)[0]
+
+
+def match_all(query, choices, match_func=None,
+              strategy=MatchStrategy.DAMERAU_LEVENSHTEIN_SIMILARITY):
+    """
+        match scores from a list or dictionary given an input
+
+        Arguments:
+            query:   string to test
+            choices: list or dictionary of choices
+
+        Returns: list of tuples (match, score)
+    """
+    match_func = match_func or fuzzy_match
+    if isinstance(choices, dict):
+        _choices = list(choices.keys())
+    elif isinstance(choices, list):
+        _choices = choices
+    else:
+        raise ValueError('a list or dict of choices must be provided')
+    matches = []
+    for c in _choices:
+        if isinstance(choices, dict):
+            matches.append((choices[c], match_func(query, c, strategy)))
+        else:
+            matches.append((c, match_func(query, c, strategy)))
+    return sorted(matches, key=lambda k: k[1], reverse=True)

nebulento-0.0.1/nebulento/version.py

@@ -0,0 +1,6 @@
+# START_VERSION_BLOCK
+VERSION_MAJOR = 0
+VERSION_MINOR = 0
+VERSION_BUILD = 1
+VERSION_ALPHA = 0
+# END_VERSION_BLOCK

nebulento-0.0.1/nebulento.egg-info/PKG-INFO

@@ -0,0 +1,89 @@
+Metadata-Version: 2.1
+Name: nebulento
+Version: 0.0.1
+Summary: dead simple fuzzy matching intent parser
+Home-page: https://github.com/OpenJarbas/nebulento
+Author: jarbasai
+Author-email: jarbasai@mailfence.com
+License: apache-2.0
+Description: # Nebulento
+        
+        *A lightweight, dead simple fuzzy matching intent parser*
+        
+        Built on top of [rapidfuzz](https://github.com/maxbachmann/rapidfuzz)
+        
+        Finds the closest matching intent via fuzzy match between the text and all of the training sentences you provided. Works best when you have a small number of sentences (dozens to hundreds) and need some resiliency to spelling errors (i.e., from text chat).
+        
+        ## Usage
+        
+        ```python
+        from nebulento import IntentContainer, MatchStrategy
+        
+        container = IntentContainer(fuzzy_strategy=MatchStrategy.TOKEN_SET_RATIO)
+        
+        container.add_intent('hello', [
+            'hello', 'hi', 'how are you', "what's up"
+        ])
+        container.add_intent('buy', [
+            'buy {item}', 'purchase {item}', 'get {item}', 'get {item} for me'
+        ])
+        container.add_entity('item', [
+            'milk', 'cheese'
+        ])
+        
+        container.calc_intent('hello')
+        # {'best_match': 'hello',
+        #  'conf': 1.0,
+        #  'entities': {},
+        #  'match_strategy': 'TOKEN_SET_RATIO',
+        #  'name': 'hello',
+        #  'utterance': 'hello',
+        #  'utterance_consumed': 'hello',
+        #  'utterance_remainder': ''}
+                                 
+        container.calc_intent('buy milk')
+        # {'best_match': 'buy {item}',
+        #  'conf': 0.71875,
+        #  'entities': {'item': ['milk']},
+        #  'match_strategy': 'TOKEN_SET_RATIO',
+        #  'name': 'buy',
+        #  'utterance': 'buy milk',
+        #  'utterance_consumed': 'buy milk',
+        #  'utterance_remainder': ''}
+        
+        
+        container.add_intent('look_at_thing', ['I see {thing} (in|on) {place}'])
+        container.add_entity("place", ["floor", "table"])
+        
+        container.calc_intent('I see trash in the floor')
+        #{'best_match': 'i see {thing} in {place}',
+        # 'conf': 0.65625,
+        # 'entities': {'place': ['floor']},
+        # 'match_strategy': 'TOKEN_SET_RATIO',
+        # 'name': 'look_at_thing',
+        # 'utterance': 'i see trash in the floor',
+        # 'utterance_consumed': 'i see in floor',
+        # 'utterance_remainder': 'trash the'}
+                    
+        container.add_entity("thing", ["food"])
+        container.calc_intent('I see food in the table')
+        #{'best_match': 'i see {thing} in {place}',
+        # 'conf': 0.7007978723404256,
+        # 'entities': {'place': ['table'], 'thing': ['food']},
+        # 'match_strategy': 'TOKEN_SET_RATIO',
+        # 'name': 'look_at_thing',
+        # 'utterance': 'i see food in the table',
+        # 'utterance_consumed': 'i see in table food',
+        # 'utterance_remainder': 'the'}
+        
+        ```
+        
+        ## Match Strategies
+        
+        - **Ratio**: Use `MatchStrategy.RATIO` when you need to compare strings and determine their overall similarity. It is effective for handling cases where strings have minor differences due to typos or spelling variations.
+        - **Partial Ratio**: `MatchStrategy.PARTIAL_RATIO` is useful when you want to focus on the best matching substring between two strings. It handles cases where one string is a subset or prefix of the other, providing a more targeted similarity measure.
+        - **Token Set Ratio**: `MatchStrategy.TOKEN_SET_RATIO` is ideal when you want to compare strings without considering their word order. It captures the essence of the strings’ content, making it suitable for scenarios where word arrangement might vary but the overall content remains similar.
+        - **Token Sort Ratio**: Use `MatchStrategy.TOKEN_SORT_RATIO` when you want to compare strings and consider word order variations. It is particularly effective when the words are expected to be similar, but their arrangement may differ.
+        
+Platform: UNKNOWN
+Description-Content-Type: text/markdown

nebulento-0.0.1/nebulento.egg-info/SOURCES.txt

@@ -0,0 +1,13 @@
+LICENSE.md
+README.md
+setup.py
+nebulento/__init__.py
+nebulento/bracket_expansion.py
+nebulento/fuzz.py
+nebulento/version.py
+nebulento.egg-info/PKG-INFO
+nebulento.egg-info/SOURCES.txt
+nebulento.egg-info/dependency_links.txt
+nebulento.egg-info/requires.txt
+nebulento.egg-info/top_level.txt
+test/test_nebulento.py

nebulento-0.0.1/nebulento.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

nebulento-0.0.1/nebulento.egg-info/requires.txt

@@ -0,0 +1,2 @@
+rapidfuzz
+quebra_frases

nebulento-0.0.1/nebulento.egg-info/top_level.txt

@@ -0,0 +1 @@
+nebulento

nebulento-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

nebulento-0.0.1/setup.py

@@ -0,0 +1,61 @@
+import os
+import os.path
+
+from setuptools import setup
+
+BASEDIR = os.path.abspath(os.path.dirname(__file__))
+
+
+def required(requirements_file):
+    """ Read requirements file and remove comments and empty lines. """
+    with open(os.path.join(BASEDIR, requirements_file), 'r') as f:
+        requirements = f.read().splitlines()
+        if 'MYCROFT_LOOSE_REQUIREMENTS' in os.environ:
+            print('USING LOOSE REQUIREMENTS!')
+            requirements = [r.replace('==', '>=').replace('~=', '>=') for r in requirements]
+        return [pkg for pkg in requirements
+                if pkg.strip() and not pkg.startswith("#")]
+
+
+def get_version():
+    version_file = os.path.join(BASEDIR, 'nebulento', 'version.py')
+    major, minor, build, alpha = (None, None, None, None)
+    with open(version_file) as f:
+        for line in f:
+            if 'VERSION_MAJOR' in line:
+                major = line.split('=')[1].strip()
+            elif 'VERSION_MINOR' in line:
+                minor = line.split('=')[1].strip()
+            elif 'VERSION_BUILD' in line:
+                build = line.split('=')[1].strip()
+            elif 'VERSION_ALPHA' in line:
+                alpha = line.split('=')[1].strip()
+
+            if ((major and minor and build and alpha) or
+                    '# END_VERSION_BLOCK' in line):
+                break
+    version = f"{major}.{minor}.{build}"
+    if int(alpha):
+        version += f"a{alpha}"
+    return version
+
+
+def get_description():
+    with open(os.path.join(BASEDIR, "README.md"), "r") as f:
+        long_description = f.read()
+    return long_description
+
+
+setup(
+    name='nebulento',
+    version=get_version(),
+    packages=['nebulento'],
+    url='https://github.com/OpenJarbas/nebulento',
+    license='apache-2.0',
+    author='jarbasai',
+    author_email='jarbasai@mailfence.com',
+    install_requires=required('requirements.txt'),
+    description='dead simple fuzzy matching intent parser',
+    long_description=get_description(),
+    long_description_content_type="text/markdown"
+)

nebulento-0.0.1/test/test_nebulento.py

@@ -0,0 +1,232 @@
+import unittest
+
+from nebulento import IntentContainer, MatchStrategy
+
+
+class TestIntentContainer(unittest.TestCase):
+    def test_syntax(self):
+        container = IntentContainer()
+        container.add_intent('hello', ["(hello|hi|hey) world"])
+        self.assertEqual(set(container.registered_intents["hello"]),
+                         set(['hello world', 'hi world', 'hey world']))
+
+        container = IntentContainer()
+        container.add_intent('hello', ["hello (world|)"])
+        self.assertEqual(set(container.registered_intents["hello"]),
+                         set(['hello world', 'hello']))
+
+        container.add_intent('hey', ["hey [world]"])
+        self.assertEqual(set(container.registered_intents["hey"]),
+                         set(['hey world', 'hey']))
+
+        container.add_intent('hi', ["hi [{person}|people]"])
+        self.assertEqual(set(container.registered_intents["hi"]),
+                         set(['hi {person}', 'hi people', 'hi']))
+
+    # test intent parsing
+    def test_intents(self):
+        container = IntentContainer()
+        container.add_intent('hello', [
+            'hello', 'hi', 'how are you', "what's up"
+        ])
+        container.add_intent('buy', [
+            'buy {item}', 'purchase {item}', 'get {item}', 'get {item} for me'
+        ])
+        container.add_entity('item', [
+            'milk', 'cheese'
+        ])
+        self.assertEqual(container.calc_intent('hello'),
+                         {'best_match': 'hello',
+                          'conf': 1.0,
+                          'entities': {},
+                          'match_strategy': 'DAMERAU_LEVENSHTEIN_SIMILARITY',
+                          'name': 'hello',
+                          'utterance': 'hello',
+                          'utterance_consumed': 'hello',
+                          'utterance_remainder': ''})
+
+        self.assertEqual(container.calc_intent('buy milk'),
+                         {'best_match': 'buy {item}',
+                          'conf': 0.625,
+                          'entities': {'item': ['milk']},
+                          'match_strategy': 'DAMERAU_LEVENSHTEIN_SIMILARITY',
+                          'name': 'buy',
+                          'utterance': 'buy milk',
+                          'utterance_consumed': 'buy milk',
+                          'utterance_remainder': ''})
+        self.assertEqual(container.calc_intent('buy beer'),
+                         {'best_match': 'buy {item}',
+                          'conf': 0.5,
+                          'entities': {},
+                          'match_strategy': 'DAMERAU_LEVENSHTEIN_SIMILARITY',
+                          'name': 'buy',
+                          'utterance': 'buy beer',
+                          'utterance_consumed': 'buy',
+                          'utterance_remainder': 'beer'}
+                         )
+
+    def test_case(self):
+        container = IntentContainer()
+        container.add_intent('test', ['Testing cAPitalizAtion'])
+        self.assertEqual(
+            container.calc_intent('Testing cAPitalizAtion')['conf'], 1.0)
+        self.assertEqual(
+            container.calc_intent('teStiNg CapitalIzation')['conf'], 1.0)
+
+        container = IntentContainer(ignore_case=False)
+        container.add_intent('test', ['Testing cAPitalizAtion'])
+        self.assertEqual(
+            container.calc_intent('teStiNg CapitalIzation')['conf'],
+            0.6363636363636364)
+
+    def test_entities(self):
+        container = IntentContainer()
+        container.add_intent('test3', ['I see {thing} (in|on) {place}'])
+        self.assertEqual(
+            container.calc_intent('I see a bin in there'),
+            {'best_match': 'i see {thing} in {place}',
+             'conf': 0.5416666666666667,
+             'entities': {},
+             'match_strategy': 'DAMERAU_LEVENSHTEIN_SIMILARITY',
+             'name': 'test3',
+             'utterance': 'i see a bin in there',
+             'utterance_consumed': 'i see in',
+             'utterance_remainder': 'a bin there'}
+        )
+        container.add_entity("place", ["floor", "table"])
+        self.assertEqual(
+            container.calc_intent('I see trash in the floor'),
+            {'best_match': 'i see {thing} in {place}',
+             'conf': 0.53125,
+             'entities': {'place': ['floor']},
+             'match_strategy': 'DAMERAU_LEVENSHTEIN_SIMILARITY',
+             'name': 'test3',
+             'utterance': 'i see trash in the floor',
+             'utterance_consumed': 'i see in floor',
+             'utterance_remainder': 'trash the'}
+        )
+        container.add_entity("thing", ["food"])
+        self.assertEqual(
+            container.calc_intent('I see food in the table'),
+            {'best_match': 'i see {thing} in {place}',
+             'conf': 0.6484375,
+             'entities': {'place': ['table'], 'thing': ['food']},
+             'match_strategy': 'DAMERAU_LEVENSHTEIN_SIMILARITY',
+             'name': 'test3',
+             'utterance': 'i see food in the table',
+             'utterance_consumed': 'i see in table food',
+             'utterance_remainder': 'the'}
+        )
+
+    # test match strategies
+    def test_token_set(self):
+        container = IntentContainer(
+            fuzzy_strategy=MatchStrategy.TOKEN_SET_RATIO)
+        container.add_intent('buy', [
+            'buy {item}', 'purchase {item}', 'get {item}', 'get {item} for me'
+        ])
+        container.add_entity('item', [
+            'milk', 'cheese'
+        ])
+        self.assertEqual(container.calc_intent('buy milk'),
+                         {'best_match': 'buy {item}',
+                          'conf': 0.6666666666666667,
+                          'entities': {'item': ['milk']},
+                          'match_strategy': 'TOKEN_SET_RATIO',
+                          'name': 'buy',
+                          'utterance': 'buy milk',
+                          'utterance_consumed': 'buy milk',
+                          'utterance_remainder': ''})
+        self.assertEqual(container.calc_intent('buy beer'),
+                         {'best_match': 'buy {item}',
+                          'conf': 0.5555555555555556,
+                          'entities': {},
+                          'match_strategy': 'TOKEN_SET_RATIO',
+                          'name': 'buy',
+                          'utterance': 'buy beer',
+                          'utterance_consumed': 'buy',
+                          'utterance_remainder': 'beer'})
+
+    def test_token_sort(self):
+        container = IntentContainer(
+            fuzzy_strategy=MatchStrategy.TOKEN_SORT_RATIO)
+        container.add_intent('buy', [
+            'buy {item}', 'purchase {item}', 'get {item}', 'get {item} for me'
+        ])
+        container.add_entity('item', [
+            'milk', 'cheese'
+        ])
+        self.assertEqual(container.calc_intent('buy milk'),
+                         {'best_match': 'buy {item}',
+                          'conf': 0.6666666666666667,
+                          'entities': {'item': ['milk']},
+                          'match_strategy': 'TOKEN_SORT_RATIO',
+                          'name': 'buy',
+                          'utterance': 'buy milk',
+                          'utterance_consumed': 'buy milk',
+                          'utterance_remainder': ''})
+        self.assertEqual(container.calc_intent('buy beer'),
+                         {'best_match': 'buy {item}',
+                          'conf': 0.33333333333333337,
+                          'entities': {},
+                          'match_strategy': 'TOKEN_SORT_RATIO',
+                          'name': 'buy',
+                          'utterance': 'buy beer',
+                          'utterance_consumed': 'buy',
+                          'utterance_remainder': 'beer'})
+
+    def test_partial_token_set(self):
+        container = IntentContainer(
+            fuzzy_strategy=MatchStrategy.PARTIAL_TOKEN_SET_RATIO)
+        container.add_intent('buy', [
+            'buy {item}', 'purchase {item}', 'get {item}', 'get {item} for me'
+        ])
+        container.add_entity('item', [
+            'milk', 'cheese'
+        ])
+        self.assertEqual(container.calc_intent('buy milk'),
+                         {'best_match': 'buy {item}',
+                          'conf': 1,
+                          'entities': {'item': ['milk']},
+                          'match_strategy': 'PARTIAL_TOKEN_SET_RATIO',
+                          'name': 'buy',
+                          'utterance': 'buy milk',
+                          'utterance_consumed': 'buy milk',
+                          'utterance_remainder': ''})
+        self.assertEqual(container.calc_intent('buy beer'),
+                         {'best_match': 'buy {item}',
+                          'conf': 1.0,
+                          'entities': {},
+                          'match_strategy': 'PARTIAL_TOKEN_SET_RATIO',
+                          'name': 'buy',
+                          'utterance': 'buy beer',
+                          'utterance_consumed': 'buy',
+                          'utterance_remainder': 'beer'})
+
+    def test_partial_token_sort(self):
+        container = IntentContainer(
+            fuzzy_strategy=MatchStrategy.PARTIAL_TOKEN_SORT_RATIO)
+        container.add_intent('buy', [
+            'buy {item}', 'purchase {item}', 'get {item}', 'get {item} for me'
+        ])
+        container.add_entity('item', [
+            'milk', 'cheese'
+        ])
+        self.assertEqual(container.calc_intent('buy milk'),
+                         {'best_match': 'buy {item}',
+                          'conf': 0.7857142857142857,
+                          'entities': {'item': ['milk']},
+                          'match_strategy': 'PARTIAL_TOKEN_SORT_RATIO',
+                          'name': 'buy',
+                          'utterance': 'buy milk',
+                          'utterance_consumed': 'buy milk',
+                          'utterance_remainder': ''})
+        self.assertEqual(container.calc_intent('buy beer'),
+                         {'best_match': 'buy {item}',
+                          'conf': 0.5454545454545454,
+                          'entities': {},
+                          'match_strategy': 'PARTIAL_TOKEN_SORT_RATIO',
+                          'name': 'buy',
+                          'utterance': 'buy beer',
+                          'utterance_consumed': 'buy',
+                          'utterance_remainder': 'beer'})