chore: package reorg

src/cli.py

@@ -1,24 +0,0 @@
-import argparse
-
-from pathlib import Path
-from server import Server
-from indexer import Indexer
-from client import search
-from settings import settings
-
-parser = argparse.ArgumentParser()
-
-parser.add_argument("command")
-parser.add_argument("--q", required=False)
-
-args = parser.parse_args()
-
-if args.command == "start":
-    watched = [Path(p).expanduser() for p in settings.WATCHED]
-    server = Server(
-        indexer=Indexer(domain=watched),
-        watched=watched,
-    )
-    server.run()
-elif args.command == "search":
-    search(args.q)

src/codesearch/cli.py

@@ -0,0 +1,30 @@
+import argparse
+
+from pathlib import Path
+from .server import Server
+from .indexer import Indexer
+from .client import search
+from .settings import settings
+
+
+def main():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("command")
+    parser.add_argument("--q", required=False)
+
+    args = parser.parse_args()
+
+    if args.command == "start":
+        watched = [Path(p).expanduser() for p in settings.WATCHED]
+        server = Server(
+            indexer=Indexer(
+                domain=watched,
+                exclusions=settings.EXCLUDES,
+                file_types=settings.FILE_TYPES,
+            ),
+            watched=watched,
+        )
+        server.run()
+    elif args.command == "search":
+        search(args.q)

src/codesearch/client.py

@@ -1,12 +1,14 @@
 import socket
 import json
-from settings import settings
 from pathlib import Path
-from colors import highlight
 
 import curses
 
 
+from .settings import settings
+from .colors import highlight
+
+
 def display_handler(stdscr, buffer):
     current_y = 0
     stdscr.refresh()

src/codesearch/indexer.py

@@ -43,6 +43,8 @@ class Indexer(IndexerBase):
     _trigram_index = attr.ib(default=attr.Factory(TrigramIndex))
     _line_index = attr.ib(default=attr.Factory(LineIndex))
 
+    _exclusions = attr.ib(default=attr.Factory(list))
+    _file_types = attr.ib(default=attr.Factory(list))
     # Document corpus
     corpus = attr.ib(default=attr.Factory(Corpus))
     domain = attr.ib(default=attr.Factory(list))
@@ -120,7 +122,7 @@ class Indexer(IndexerBase):
         current = Path(path_root)
 
         # Avoid any excluded paths
-        if any([current.match(x) for x in settings.EXCLUDES]):
+        if any([current.match(x) for x in self._exclusions]):
             logger.info(f"{path_root} excluded.", prefix="Discovery")
             return []
 
@@ -130,7 +132,7 @@ class Indexer(IndexerBase):
 
             return collected
 
-        if current.suffix not in settings.FILE_TYPES:
+        if current.suffix not in self._file_types:
             return []
 
         logger.info(f"Collected {path_root}", prefix="Discovery")

src/codesearch/prefix_tree.py

@@ -2,6 +2,7 @@ import json
 
 import attr
 
+
 @attr.s
 class PrefixTree:
     root = attr.ib()
@@ -49,7 +50,6 @@ class PrefixTree:
 
     def to_json(self):
         return json.dumps(self.to_dict())
-        
 
 
 @attr.s
@@ -59,4 +59,8 @@ class PrefixTreeNode:
     children = attr.ib(default=attr.Factory(dict))
 
     def to_dict(self):
-        return {"value": self.value, "mappings": self.mappings, "children": [child.to_dict() for child in self.children.values()]}
+        return {
+            "value": self.value,
+            "mappings": self.mappings,
+            "children": [child.to_dict() for child in self.children.values()],
+        }

src/codesearch/server.py

@@ -2,13 +2,13 @@ import json
 import socket
 import pyinotify
 import attr
-from watcher import WatchHandler
-from indexer import Indexer
-from constants import QUERY_STRING_LENGTH
+from codesearch.watcher import WatchHandler
+from codesearch.indexer import Indexer
+from codesearch.constants import QUERY_STRING_LENGTH
 from pathlib import Path
-from settings import settings
+from codesearch.settings import settings
 
-from logger import get_logger
+from codesearch.logger import get_logger
 
 logger = get_logger(__name__)
 

src/codesearch/test_indexer.py

@@ -0,0 +1,49 @@
+import pytest
+
+from .indexer import Indexer
+
+
+@pytest.fixture()
+def indexer():
+    return Indexer()
+
+
+def test_indexer_builds_trigram_set_for_given_document(indexer):
+    mock_document = "now that's a doc"
+    mock_path = "/home/documents/cool_doc"
+
+    indexer.index(path=mock_path, content=mock_document)
+
+    expected_trigrams = [
+        "now",
+        "ow ",
+        "w t",
+        " th",
+        "tha",
+        "hat",
+        "at'",
+        "t's",
+        "'s ",
+        "s a",
+        " a ",
+        "a d",
+        " do",
+        "doc",
+    ]
+
+    assert indexer.trigrams == {mock_path: set(expected_trigrams)}
+
+
+def test_indexer_preserves_previous_trigram_sets_on_index(indexer):
+    mock_document_1 = "wow"
+    mock_document_2 = "woa"
+    mock_path_1 = "/home"
+    mock_path_2 = "/somewhere_else"
+
+    indexer.index(path=mock_path_1, content=mock_document_1)
+
+    assert indexer.trigrams == {mock_path_1: set(["wow"])}
+
+    indexer.index(path=mock_path_2, content=mock_document_2)
+
+    assert indexer.trigrams == {mock_path_1: set(["wow"]), mock_path_2: set(["woa"])}

src/codesearch/test_prefix_tree.py

@@ -2,58 +2,66 @@ import pytest
 
 from .prefix_tree import PrefixTree
 
+
 @pytest.fixture
 def prefix_tree():
     return PrefixTree.initialize()
 
+
 def test_base_tree_has_a_root_node(prefix_tree, snapshot):
     assert prefix_tree.to_dict() == snapshot
 
+
 def test_insert_single_string(prefix_tree, snapshot):
-    mock_value = 'abc'
-    mock_key = 'key_1'
+    mock_value = "abc"
+    mock_key = "key_1"
     prefix_tree.insert(value=mock_value, key=mock_key)
     assert prefix_tree.to_dict() == snapshot
     assert prefix_tree.get(value=mock_value) == [mock_key]
 
+
 def test_insert_single_character_(prefix_tree, snapshot):
-    mock_value = 'a'
-    mock_key = 'key_1'
+    mock_value = "a"
+    mock_key = "key_1"
     prefix_tree.insert(value=mock_value, key=mock_key)
     assert prefix_tree.to_dict() == snapshot
     assert prefix_tree.get(value=mock_value) == [mock_key]
 
+
 def test_insert_overlapping_strings(prefix_tree, snapshot):
-    mock_value_1 = 'abcd'
-    mock_key_1 = 'key_1'
-    mock_value_2 = 'abce'
-    mock_key_2 = 'key_2'
+    mock_value_1 = "abcd"
+    mock_key_1 = "key_1"
+    mock_value_2 = "abce"
+    mock_key_2 = "key_2"
     prefix_tree.insert(value=mock_value_1, key=mock_key_1)
     prefix_tree.insert(value=mock_value_2, key=mock_key_2)
     assert prefix_tree.to_dict() == snapshot
     assert prefix_tree.get(value=mock_value_1) == [mock_key_1]
     assert prefix_tree.get(value=mock_value_2) == [mock_key_2]
 
+
 def test_insert_multiple_keys_same_string(prefix_tree, snapshot):
-    mock_value = 'abcd'
-    mock_key_1 = 'key_1'
-    mock_key_2 = 'key_2'
+    mock_value = "abcd"
+    mock_key_1 = "key_1"
+    mock_key_2 = "key_2"
     prefix_tree.insert(value=mock_value, key=mock_key_1)
     prefix_tree.insert(value=mock_value, key=mock_key_2)
     assert prefix_tree.to_dict() == snapshot
     assert prefix_tree.get(value=mock_value) == [mock_key_1, mock_key_2]
 
+
 def test_insert_strings_subsets_of_each_other(prefix_tree, snapshot):
-    mock_value_1 = 'abcd'
-    mock_key_1 = 'key_1'
-    mock_value_2 = 'abc'
-    mock_key_2 = 'key_2'
+    mock_value_1 = "abcd"
+    mock_key_1 = "key_1"
+    mock_value_2 = "abc"
+    mock_key_2 = "key_2"
     prefix_tree.insert(value=mock_value_1, key=mock_key_1)
     prefix_tree.insert(value=mock_value_2, key=mock_key_2)
     assert prefix_tree.to_dict() == snapshot
     assert prefix_tree.get(value=mock_value_1) == [mock_key_1]
     assert prefix_tree.get(value=mock_value_2) == [mock_key_2]
 
+
 def test_serializes_to_json(prefix_tree, snapshot):
     prefix_tree.insert(value="abcd", key="key_1")
     assert prefix_tree.to_json() == snapshot

src/codesearch/watcher.py

@@ -1,7 +1,7 @@
 import pyinotify
 import attr
 
-from logger import get_logger
+from .logger import get_logger
 
 logger = get_logger(__name__)
 

src/setup.py

@@ -0,0 +1,9 @@
+from setuptools import setup
+
+setup(
+    name="codesearch",
+    version="0.1",
+    packages=["codesearch"],
+    install_requires=["pyinotify", "attr"],
+    entry_points={"console_scripts": ["codesearch=codesearch.cli:main"]},
+)