update

.github/workflows/compre-test.yml

@@ -0,0 +1,35 @@
+name: tests
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [ '3.7' ]
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 pytest
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      - name: Lint with flake8
+        run: |
+          # stop the build if there are Python syntax errors or undefined names
+          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+      - name: Test with pytest
+        run: |
+          pytest -W ignore::DeprecationWarning

cathodedataextractor/nlp/cner.py

@@ -141,6 +141,8 @@ def prompt_tag(self, cem: str, normalize=False) -> str:
             return 'element'
         elif cem in ELEMENTS_NAMES_UL:
             return 'element_name'
+        elif cem in POLYATOMIC_IONS:
+            return 'polyatomic_ions'
         elif cem in SIMPLE_COMPOUND:
             return 'simple'
         elif self.is_word(cem):
@@ -164,29 +166,28 @@ def __generalized_elements(cem: str):
         if normalize:
             cem = self.normalized_compound_formula(cem)
         shape = word_shape(cem)
-        likely_abb = True if 'XXX' in shape else False
+        likely_abb = any_func(shape, ABB_SHAPE)
         if not likely_abb and (shape.startswith('d') or 'b.b' in shape):
             return 'other'
+        elif 'Xx-Xx-Xx' in shape:  # Nax(Cu-Fe-Mn)O2
+            return 'irregular_shape'
         parse_ = self.is_compound_formula(cem)
-        if parse_ and parse_[1]:
+        if not likely_abb and parse_ and parse_[1]:
             # NaCoMnO   NaMnNiCuFeTiOF
             if len([i for i in parse_[1] if i in TRANSITION_ME]) >= 2 and parse_[0] == ''.join(
                     parse_[1]):
                 return 'is_likely_abbreviation'
             # 'Na/Li/Ni/Mn/Co'
-            elif set(cem.split('/')).difference(ELEMENTS):
+            elif not set(cem.split('/')).difference(ELEMENTS):
                 return 'synthetic'
-            # Nax(Cu-Fe-Mn)O2
-            elif 'Xx-Xx-Xx' in shape or all(len(i) <= 2 for i in cem.split('-')):
+            elif all(len(i) <= 2 for i in cem.split('-')):
                 return 'irregular_shape'
             elif '/' not in cem:
                 return 'synthetic'
             else:
                 return 'other'
         elif un_chem_abbreviation.search(cem):
             return 'other'
-        elif '-' in cem and 'Xx-Xx-Xx' in shape:
-            return 'irregular_shape'
         elif any_func(cem, SOLVENT_NAMES):
             return 'solvent_names'
         elif any_func(cem, RAW_MATERIAL):
@@ -196,8 +197,6 @@ def __generalized_elements(cem: str):
         elif cem in OTHER or any_func(cem, OTHER_IN) or pattern.match(cem):
             return 'other'
 
-        likely_abb_ = any_func(shape, ABB_SHAPE)
-
         if not likely_abb:
             try:
                 _elements = [element.value for element in Composition(cem).elements]
@@ -214,7 +213,7 @@ def __generalized_elements(cem: str):
                     return 'raw_material'
             except (ValueError, AttributeError, KeyError):
                 ele_result = {}
-                if self.prompt_element in cem and not likely_abb_:
+                if self.prompt_element in cem and not likely_abb:
                     ele_result = __generalized_elements(cem)
                     if len(ele_result) > 2 and 'O' in ele_result:
                         if 'M' in ele_result:
@@ -227,11 +226,11 @@ def __generalized_elements(cem: str):
                 if 'Xx*Xx' in shape:
                     return 'other'
                 elif self.prompt_element in cem or self.prompt_element[0] in cem:
-                    if not ele_result or likely_abb_:
+                    if not ele_result or likely_abb:
                         return 'is_likely_abbreviation'
                     else:
                         return 'raw_material'
-        return 'is_likely_abbreviation' if likely_abb_ or shape in ['XX', 'Xd.d'] and not any_func(cem, ['=',
+        return 'is_likely_abbreviation' if likely_abb or shape in ['XX', 'Xd.d'] and not any_func(cem, ['=',
                                                                                                          ',']) else 'other'
 
     @staticmethod

cathodedataextractor/parse/regex_functions.py

@@ -48,7 +48,7 @@ def end_parentheses(cem: str):
 
 @lru_cache(None)
 def polyatomic_ions(string):
-    return any(_ == string for _ in set(POLYATOMIC_IONS))
+    return any(_ == string for _ in POLYATOMIC_IONS)
 
 
 @lru_cache(None)

cathodedataextractor/parse/regex_pattern.py

@@ -66,7 +66,7 @@
     "other_me": ['B', 'Al', 'Ga', 'In', 'Tl', 'Si', 'Ge', 'Sn', 'Pb', 'As', 'Sb', 'Bi', 'Te'],
 }
 
-POLYATOMIC_IONS = ['CO3', 'PO4', 'PO3', 'P2O7', 'NH4', 'NO3', 'NO2', 'SO4', 'SO3', 'OH', 'CN', 'SiO4']
+POLYATOMIC_IONS = {'CO3', 'PO4', 'PO3', 'P2O7', 'NH4', 'NO3', 'NO2', 'SO4', 'SO3', 'OH', 'CN', 'SiO4'}
 SIMPLE_COMPOUND = ['NaHO', 'NaCl', 'NaF', 'NaBr', 'Na2S2', 'Na2CO3']
 # m_anions = ['H2PO4', 'HPO4', 'HCO3', 'HSO4', 'HSO3', 'C2O4']
 # d_anions = ['CO3', 'PO4', 'PO3', 'NH4', 'NO3', 'NO2', 'SO4', 'SO3', 'OH', 'CN']
@@ -84,15 +84,15 @@
 GREEK_CHARS = {chr(i) for i in range(945, 970)}
 
 OTHER = {'JCPDS', 'JCPSD', 'RT', 'SOC', 'ICP', 'SIB', 'DFT', 'STA', 'ICSD', 'HITACH', 'NIST', 'PAL', 'TXM', 'SXRPD',
-         'PVDF', 'DFPT', 'CNTs', 'USP', 'ALD', 'PH3', 'CV', 'CS', 'PC', 'OC', 'CB', 'ND', 'TG', 'NPs'}
+         'PVDF', 'DFPT', 'CNTs', 'USP', 'ALD', 'PH3', 'CV', 'CS', 'PC', 'OC', 'CB', 'ND', 'TG', 'NPs',
+         'Na-rich', 'Na-ion'}
 
 OTHER_IN = ['PDF', 'No.', '↔', 'Nae', 'Fig',
-            'Na-',  # Na-rich Na-ion
             'AB',  # AB ABCABC...
             'Non',  # Non-sub
             ]
 
-ABB_SHAPE = ['XXdd', 'XXX', 'XXd', 'XxXX']
+ABB_SHAPE = ['XXdd', 'XXX', 'XXd', 'XxXX', 'Xddd']
 
 NUMBER_REGEX = r'\d++[\d. ]*+'
 

tests/__init__.py

@@ -0,0 +1 @@
+# coding=utf-8

tests/resources/__init__.py

@@ -0,0 +1,3 @@
+import os
+
+TEST_PATH = os.path.dirname(__file__)