adding tests

Author: Dylan

README.md

@@ -68,7 +68,7 @@ print(result) # [[<Quantity(1.23, 'gram / centimeter ** 3')>, <Quantity(25, 'deg
 
 ### Merging Quantities
 
-Some times when you are doing parsing, you get multiple values from the parser. So it would be nice to reduce it 
+Sometimes when you are doing parsing, you get multiple values from the parser. So it would be nice to reduce it 
 down just to one value/value+condition/series+condition. `reduce_quantities` does exactly that!
 
 It will group approximate equivalent quantities and throw out bad units (units that are not like the most common). 
@@ -77,14 +77,14 @@ You can select your preference for return priority with the `order` parameter.
 ```python
 from unit_parse import Quantity, reduce_quantities
 
-quantities = [Quantity("68 degree_Fahrenheit"), Quantity("68.0 degree_Fahrenheit"), Quantity("20.0 degree_Celsius"),
+quantities = [Quantity("68 degF"), Quantity("68.0 degF"), Quantity("20.0 degC"),
               Quantity("293.15 kelvin * speed_of_light ** 2")]
 
 result = reduce_quantities(quantities)
-print(result)  # Quantity("68 degF")],
+print(result)  # Quantity("68 degF")
 ```
 
-
+---
 ---
 ## Logging
 
@@ -164,16 +164,104 @@ Output:
 Yep, there's alot of them! 
 
 ```python
-    # Simple conversions
-    5 -> 5 dimensionless
-    5 g -> 5 gram
-    5 g/ml -> 5.0 gram / milliliter
-    1 K -> 1 kelvin
-
-    # stuff
+# Simple conversions
+    5 --> 5
+    5 g --> 5 g
+    5 g/ml --> 5.0 g / ml
+    1 K --> 1 K
+    40 °F --> 40 °F
+    -40 °F --> -40 °F
+    170°C --> 170 °C
+    40°F --> 40 °F
+    20.80 mmHg --> 20.8 mmHg
+    20.80 mm Hg --> 20.8 mmHg
+# scientific notation
+    15*10**2 s --> 1500 s
+    15*10^2 s --> 1500 s
+    15 10**2 s --> 1500 s
+    8.20x10**+1 ppm --> 82.0 ppm
+    8.20x10+1 ppm --> 82.0 ppm
+    5e1 g/mol --> 50.0 g / mol
+    5E1 g/mol --> 50.0 g / mol
+    5 e1 g/mol --> 50.0 g / mol
+    5 E1 g/mol --> 50.0 g / mol
+    5e+1 g/mol --> 50.0 g / mol
+    5E-1 g/mol --> 0.5 g / mol
+    −66.11·10-62 ml/mol --> -6.611e-61 ml / mol
+    −66.11·10+62 ml/mol --> -6.611e+63 ml / mol
+    −66.11·1062 ml/mol --> -6.611e+63 ml / mol
+# messed up units/ units with powers
+    2.3 gcm --> 2.3 cm * g
+    5e5 gmol/s --> 500000.0 g * mol / s
+    2.3 gcm**3 --> 2.3 cm ** 3 * g
+    2.3 gcm**3 --> 2.3 cm ** 3 * g
+    2.3     g --> 2.3 g
+    1.10*10**-05 atm-m**3/mole --> 1.1000000000000001e-05 atm * m ** 3 / mol
+    -54.6e-5 atm-m**3/mole --> -0.000546 atm * m ** 3 / mol
+    2.3 mlgcm --> 2.3 cm * g * ml
+    42.3 gcm-3 --> 42.3 g / cm ** 3
+    42.3 g cm-3 --> 42.3 g / cm ** 3
+    −66.11·10-62 cm3/mol --> -6.611e-61 cm ** 3 / mol
+    −66.11·10+62 cm3/mol --> -6.611000000000001e+63 cm ** 3 / mol
+    −66.11·1062 cm3/mol --> -6.611000000000001e+63 cm ** 3 / mol
+    345.234 KCAL/MOLE --> 345.234 kcal / mol
+# parenthesis (brackets turn into parenthesis)
+    (4.0 °C) --> 4.0 °C
+    [4.0 °C] --> 4.0 °C
+    4.0 (°C) --> 4.0 °C
+    4.0 (°C)) --> 4.0 °C
+    )4.0 (°C) --> 4.0 °C
+    (4.0 (°C) --> 4.0 °C
+    ()4.0 (°C) --> 4.0 °C
+    4.0 °C [39.2 g/[mol * s]] --> [[<Quantity(4.0, 'degree_Celsius')>, <Quantity(39.2, 'gram / mole / second')>]]
+    1.0722 at 68 °F (EPA, 1998) --> [[1.0722, <Quantity(68, 'degree_Fahrenheit')>]]
+# conditions
+    37.34 kJ/mole (at 25 °C) --> [[<Quantity(37.34, 'kilojoule / mole')>, <Quantity(25, 'degree_Celsius')>]]
+    20.8 mm Hg @ 25 °C --> [[<Quantity(20.8, 'millimeter_Hg')>, <Quantity(25, 'degree_Celsius')>]]
+    20.8 mm Hg (25 °C) --> [[<Quantity(20.8, 'millimeter_Hg')>, <Quantity(25, 'degree_Celsius')>]]
+    20.8 mm Hg at 25 °C --> [[<Quantity(20.8, 'millimeter_Hg')>, <Quantity(25, 'degree_Celsius')>]]
+    -4,395.63 kJ/mol at 25 °C --> [[<Quantity(-4395.63, 'kilojoule / mole')>, <Quantity(25, 'degree_Celsius')>]]
+# list of quantities
+    18 mm Hg; 20 mm Hg --> [<Quantity(18, 'millimeter_Hg')>, <Quantity(20, 'millimeter_Hg')>]
+    18 mm Hg; 20 mm Hg --> [<Quantity(18, 'millimeter_Hg')>, <Quantity(20, 'millimeter_Hg')>]
+    18 mm Hg @ 68 °F; 20 mm Hg @ 77° F --> [[<Quantity(18, 'millimeter_Hg')>, <Quantity(68, 'degree_Fahrenheit')>], [<Quantity(20, 'millimeter_Hg')>, <Quantity(77, 'degree_Fahrenheit')>]]
+    18 mm Hg @ 68 °F ; 20 mm Hg @ 77° F (NTP, 1992) --> [[<Quantity(18, 'millimeter_Hg')>, <Quantity(68, 'degree_Fahrenheit')>], [<Quantity(20, 'millimeter_Hg')>, <Quantity(77, 'degree_Fahrenheit')>]]
+    18 mm Hg at 68 °F ; 20 mm Hg at 77 °F --> [[<Quantity(18, 'millimeter_Hg')>, <Quantity(68, 'degree_Fahrenheit')>], [<Quantity(20, 'millimeter_Hg')>, <Quantity(77, 'degree_Fahrenheit')>]]
+    Low threshold= 13.1150 mg/cu m; High threshold= 26840 mg/cu m; Irritating concn= 22875 mg/cu m. --> 22875.0 mg / m ** 3
+# ranges
+    115.2-115.3 °C --> 115.2 °C
+    115.2 - 115.3 °C --> 115.2 °C
+# words
+    8.20x10+1 ppm; pure --> 82.0 ppm
+    40 °F (NTP, 1992) --> 40 °F
+    4.0 °C (39.2 °F) - closed cup --> 4.0 °C
+    4.0 °C [39.2 g/[mol * s]] - closed cup --> [[<Quantity(4.0, 'degree_Celsius')>, <Quantity(39.2, 'gram / mole / second')>]]
+    4.0 °C [39.2 g/[mol * s] approx.] - closed cup --> [[<Quantity(4.0, 'degree_Celsius')>, <Quantity(39.2, 'gram / mole / second')>]]
+    4.0 °C [39.2g/[mol*s] approx.] - closed cup --> [[<Quantity(4.0, 'degree_Celsius')>, <Quantity(39.2, 'gram / mole / second')>]]
+    4.0 °C [39.2g/[mol*s]approx.] - closed cup --> [[<Quantity(4.0, 'degree_Celsius')>, <Quantity(39.2, 'gram / mole / second')>]]
+    Detection in water: 0.73 ppm; Chemically pure --> 0.73 ppm
+    Odor Threshold Range: 0.15 to 25 ppm --> 0.15 ppm
+    0.05 ppm purity specified --> 0.05 ppm
+    Odor detection in air, 0.05 ppm (purity not specified) --> 0.05 ppm
+    Relative density (water = 1): 1.04-1.13 --> 1.04
+    Density approximately 6.5 lb / gal. --> 6.5 lb / gal
+# duplicates of same quantity different units
+    4.0 °C (39.2 °F) --> 4.0 °C
+    -7991 cal/g = -334.6X10+5 J/KG --> -33460000.000000004 J / kg
+# complex
+    18 mm Hg at 68 °F ; 20 mm Hg at 77° F (NTP, 1992) --> [[<Quantity(18, 'millimeter_Hg')>, <Quantity(68, 'degree_Fahrenheit')>], [<Quantity(20, 'millimeter_Hg')>, <Quantity(77, 'degree_Fahrenheit')>]]
+    Sound travels at 0.34 km/s --> 0.34 km / s
+    Pass me a 300 ml beer. --> 300 ml
 ```
 
 
+Stuff it gets wrong. No one is perfect!
+```python
+Index of refraction: 1.50920 @ 20 °C/D --> [[1.5092, <Quantity(293.15, 'kelvin / debye')>]]
+Vapor pressure, kPa at 20 °C: 2.0 --> 2.0
+```
+
+---
 ---
 ## Configuration
 
@@ -272,7 +360,7 @@ result = unit_parse.parser("100 MOL")  # pint is case-sensitive, so this will re
 print(result)  # Quantity("100 mole")
 ```
 
-
+---
 ---
 ## Notes
 

dev_files/main.py

@@ -52,7 +52,7 @@
     ['−66.11·1062 cm3/mol', Quantity('-66.11*10**62 cm**3/mol')],
     ["345.234 KCAL/MOLE", Quantity("345.234 kcal/mole")],
 
-    # parenthesis (brackets turned to parenthesis)
+    # parenthesis (brackets turn into parenthesis)
     ["(4.0 °C)", Quantity("4 degC")],
     ["[4.0 °C]", Quantity("4 degC")],
     ["4.0 (°C)", Quantity("4 degC")],
@@ -99,6 +99,7 @@
     ["0.05 ppm purity specified", Quantity("0.05 part_per_million")],
     ["Odor detection in air, 0.05 ppm (purity not specified)", Quantity("0.05 part_per_million")],
     ["Relative density (water = 1): 1.04-1.13", Quantity("1.04")],
+    ["Density approximately 6.5 lb / gal.", Quantity("6.5 lb/ gal")],
 
     # duplicates of same quantity different units
     ["4.0 °C (39.2 °F)", Quantity("4 degC")],
@@ -118,7 +119,6 @@
 ]
 
 
-
 def pre_process_values():
     for example in examples:
         result = parser(example[0])
@@ -130,4 +130,4 @@ def main():
 
 
 if __name__ == '__main__':
-    main()
+    pre_process_values()

dev_files/reduce_quantity_list.py

@@ -4,7 +4,7 @@
 from unit_parse import logger, Q, U, reduce_quantities
 
 test_logger.setLevel(logging.DEBUG)
-logger.setLevel(logging.WARNING)
+logger.setLevel(logging.INFO)
 
 examples = [  # [Input, Output]
     # positive control (works, does changes)
@@ -49,19 +49,44 @@
       [[Q("18 mmHg"), Q("68 degF")], [Q("20 mmHg"), Q("77.0 degF")]], [Q("20.8 mmHg"), Q("25 degC")]],
      [[Q("18 mmHg"), Q("68 degF")], [Q("20 mmHg"), Q("77.0 degF")]]],
 
+    [[[[Q("68 degF"), Q("760.0 mmHg")]], Q("68.0 degF"), Q("20.0 degC"), Q("293.15 kelvin * speed_of_light ** 2"),
+      Q("68 degF"), Q("68 degF")],
+     [[Q("68 degF"), Q("760.0 mmHg")]]],
+
     [[[Q("68 degF"), Q("760.0 mmHg")], Q("68.0 degF"), Q("20.0 degC"), Q("293.15 kelvin * speed_of_light ** 2"),
       Q("68 degF"), Q("68 degF")],
-     [Q("68 degF"), Q("760.0 mmHg")]],
+     Q("68 degF")],
 
     [[0.65, Q('0.66'), Q('0.65'), Q('0.65')], Q('0.65')],
 
-    [[[0.65, Q('25  degC')], Q('0.65'), Q('0.65')], [0.65, Q('25  degC')]],
+    [[[0.65, Q('25  degC')], Q('0.65'), Q('0.65')], Q('0.65')],
+
+    [[[Q('50  kg'), Q('25  kg')], Q('0.65 dimensionless'), Q('0.65 dimensionless')],
+     [Q('50  kg'), Q('25  kg')]],
+
+    [[6, 5, 5, 3, 4, 5], 5],
+    [[6, 5, 3, 4, 7], 5],
+    [[[6, 5, 5, 3, 4, 5], 5, 6], [6, 5, 5, 3, 4, 5]],
+    [[Q("1 g"), Q("2 g"), Q("3 g"), Q("4 g"), Q("5 g")], Q("3 g")],
+    [[[Q("6 g"), Q("6 g"), Q("5 g"), Q("5.5 g"), Q("6.2 g")], Q("6")],
+     [Q("6 g"), Q("6 g"), Q("5 g"), Q("5.5 g"), Q("6.2 g")]],
+
+    [[[[Q("-15 degC"), Q("1 mmHg")]], Q("-41.6 degC"), Q("-42 degC"), Q("-40 degC"), Q("-40 degC")],
+     [[Q("-15 degC"), Q("1 mmHg")]]],
+
+    [[[[Q("-1500 degC"), Q("1 mmHg")]], Q("-41.6 degC"), Q("-42 degC"), Q("-40 degC"), Q("-40 degC")],
+     Q("-40 degC")],
 
-    [[[Q('50  kg'), Q('25  degC')], Q('0.65 dimensionless'), Q('0.65 dimensionless')],
-     [Q('50  kg'), Q('25  degC')]]
 
     # negative control (fails/ does no changes)
+    [Q('25  degC'), Q('25  degC')],
+    [[Q('25  degC')], Q('25  degC')]
 
 ]
 
 testing_func(reduce_quantities, examples)
+
+
+# input_ = [[[Q("2 ppm"), Q("5 mol/ml"), Q("10 mol/cm**3")], Q("2 ppm"), {"order": (1, 2, 3, 0)}]]
+#
+# testing_func(reduce_quantities, input_)

dev_files/single.py

@@ -23,7 +23,7 @@
 # ]
 # testing_func(remove_words, test_remove_words, {"words": config.english_dict})
 
-result = parser("1.0722 at 68 °F (EPA, 1998)")
+result = parser("Density approximately 6.5 lb / gal.")
 
 print(result)
 

pyproject.toml

@@ -20,6 +20,13 @@ exclude_lines = [
     "if __name__ == .__main__.:"
     ]
 
+[tool.coverage.run]
+omit = [
+    "src/unit_parse/logger.py",
+    "src/unit_parse/config.py",
+    "src/unit_parse/support_files/*"
+]
+
 [tool.mypy]
 mypy_path = "src"
 check_untyped_defs = true

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = unit_parse
-version = 0.0.9
+version = 0.1.0
 description = Parse units from strings. From mess to order!
 long_description = file: README.md
 long_description_content_type = text/markdown
@@ -34,4 +34,5 @@ testing =
     flake8>=3.9
 
 [flake8]
-max-line-length = 160
+max-line-length = 160
+exclude = /unit_parse/support_files

src/__init__.py

@@ -4,5 +4,5 @@
 from unit_parse.reduce_quantities import reduce_quantities
 
 __all__ = [
-     "Unit", "U", "Q", "Quantity", "parser", "logger", "reduce_quantities"
+     "Unit", "U", "Q", "Quantity", "parser", "logger", "reduce_quantities", "config"
 ]

src/unit_parse/__init__.py

@@ -1,28 +1,26 @@
 import os
 import sys
+import inspect
 
 from unit_parse.logger import logger
 
 
-def _get_from_stack(obj):
+def get_unit_registry():
     """
     Gets object from Python stack/globals
     Stops at first object it finds
 
     """
-    for i in range(100):  # 100 is to limit the depth it looks
-        frames = sys._getframe(i)
-        globals_ = frames.f_globals
-        found_obj = [globals_[k] for k, v in globals_.items() if isinstance(v, obj) and k[0] != "_"]
-        if found_obj:
-            found_obj = found_obj[0]
-            break
+    stack = inspect.stack()
+    for frame in stack:
+        attrs: dict = frame.frame.f_locals
+        for attr in attrs.values():
+            if hasattr(attr, "_REGISTRY"):
+                return attr._REGISTRY
     else:
-        mes = f"{obj} not found in globals."
+        mes = "Pint UnitRegistry not found."
         raise Exception(mes)
 
-    return found_obj
-
 
 def check_for_pint():
     """ Check for Pint
@@ -41,18 +39,20 @@ def check_for_pint():
         logger.warning("'Pint' module found in stack. (you have 'import pint' somewhere in your code).")
         # get unit registry
         try:
-            u = _get_from_stack(modules["pint.registry"].UnitRegistry)
+            u_ = get_unit_registry()
             logger.warning("\033[32m Unit registry found. :) \033[0m")
-            return u
+            return u_
         except Exception:
             logger.warning("Pint unit registry not found in stack. Loading 'unit_parser' registry. (Note: "
                            "Pint unit registries are not interoperable. ")
 
     # if no pint found, load local
     import pint
     current_path = os.path.dirname(os.path.realpath(__file__))
-    return pint.UnitRegistry(autoconvert_offset_to_baseunit=True,
+    u_ = pint.UnitRegistry(autoconvert_offset_to_baseunit=True,
                              filename=os.path.join(current_path, "support_files\\default_en.txt"))
+    u_.default_format = "~"
+    return u_
 
 
 # set pint units
@@ -99,8 +99,8 @@ def __init__(self):
             ["°C", "degC"],  # eliminates issue with capitalization step
             ["(?<=[0-9]{1})[ ]{0,1}X[ ]{0,1}(?=[0-9]{1})", "*"],  # unify multiplication symbols
             ["(?<=[0-9]{1})[ ]{0,1}x[ ]{0,1}(?=[0-9]{1})", "*"],  # unify multiplication symbols
-            ["\[", "("],  # make all brackets parenthesis
-            ["\]", ")"],  # make all brackets parenthesis
+            ["\[", "("],  # noqa: W605 # make all brackets parenthesis
+            ["\]", ")"],  # noqa: W605 # make all brackets parenthesis
             ["^.*={1}", ""],  # delete everything in front of equal
             ["^.*:{1}", ""],  # delete everything in front of collen
             ["( to )", "-"],   # unify how range are represented

src/unit_parse/config.py

@@ -8,10 +8,10 @@
 from typing import List, Union
 import re
 
-from .config import Unit, Quantity, config
-from .pre_processing_substitution import sub_general
-from .utils import flatten_list, contains_number, sig_figs, remove_empty_str, split_list
-from .logger import log_debug, log_info, logger
+from unit_parse.config import Unit, Quantity, config
+from unit_parse.pre_processing_substitution import sub_general
+from unit_parse.utils import flatten_list, contains_number, sig_figs, remove_empty_str, split_list
+from unit_parse.logger import log_debug, log_info, logger
 
 
 @log_info
@@ -341,7 +341,7 @@ def split_on_multiplication_symbol(text_in: Union[str, list[str], list[Union[str
                     except Exception:
                         pass
                     if bool(re.match("([^*]+)[ ]?[*][ ]?([^*-0-9].*)", split)):
-                        new_splits[ii] = split_on_multiplication_symbol(split)  # recursive
+                        new_splits[ii] = split_on_multiplication_symbol(split)  # pragma: no cover  recursive
 
                 text_in[i] = new_splits
                 continue