Switched transforming prefix to standard to use the symbol instead of the name (#238)

* Added a test for mu, and switched transforming prefix to standard to use the symbol instead of the name

* Reverted change

* Removed old TODO statement

* Fixed micro to be able to be used as a prefix

* Fixed preview for physical quantities

Author: m-messer

app/context/physical_quantity.py

@@ -6,7 +6,7 @@
 from copy import deepcopy
 from ..utility.physical_quantity_utilities import (
     SLR_quantity_parser,
-    SLR_quantity_parsing
+    SLR_quantity_parsing, expression_preprocess
 )
 from ..preview_implementations.physical_quantity_preview import preview_function
 from ..feedback.physical_quantity import feedback_string_generators as physical_quantity_feedback_string_generators
@@ -476,107 +476,6 @@ def feedback_procedure_generator(parameters_dict):
         graphs.update({label: graph})
     return graphs
 
-def preprocess_legacy(expr, parameters):
-    prefix_data = {(p[0], p[1], tuple(), p[3]) for p in set_of_SI_prefixes}
-    prefixes = []
-    for prefix in prefix_data:
-        prefixes = prefixes + [prefix[0]] + list(prefix[-1])
-    prefix_short_forms = [prefix[1] for prefix in prefix_data]
-    unit_data = set_of_SI_base_unit_dimensions \
-                | set_of_derived_SI_units_in_SI_base_units \
-                | set_of_common_units_in_SI \
-                | set_of_very_common_units_in_SI \
-                | set_of_imperial_units
-    unit_long_forms = prefixes
-    for unit in unit_data:
-        unit_long_forms = unit_long_forms + [unit[0]] + list(unit[-2]) + list(unit[-1])
-    unit_long_forms = "(" + "|".join(unit_long_forms) + ")"
-    # Rewrite any expression on the form "*UNIT" (but not "**UNIT") as " UNIT"
-    # Example: "newton*metre" ---> "newton metre"
-    search_string = r"(?<!\*)\* *" + unit_long_forms
-    match_content = re.search(search_string, expr[1:])
-    while match_content is not None:
-        expr = expr[0:match_content.span()[0] + 1] + match_content.group().replace("*", " ") + expr[
-                                                                                               match_content.span()[
-                                                                                                   1] + 1:]
-        match_content = re.search(search_string, expr[1:])
-    prefixes = "(" + "|".join(prefixes) + ")"
-    # Rewrite any expression on the form "PREFIX UNIT" as "PREFIXUNIT"
-    # Example: "kilo metre" ---> "kilometre"
-    search_string = prefixes + " " + unit_long_forms
-    match_content = re.search(search_string, expr)
-    while match_content is not None:
-        expr = expr[0:match_content.span()[0]] + " " + "".join(match_content.group().split()) + expr[
-                                                                                                match_content.span()[
-                                                                                                    1]:]
-        match_content = re.search(search_string, expr)
-    unit_short_forms = [u[1] for u in unit_data]
-    short_forms = "(" + "|".join(list(set(prefix_short_forms + unit_short_forms))) + ")"
-    # Add space before short forms of prefixes or unit names if they are preceded by numbers or multiplication
-    # Example: "100Pa" ---> "100 Pa"
-    search_string = r"[0-9\*\(\)]" + short_forms
-    match_content = re.search(search_string, expr)
-    while match_content is not None:
-        expr = expr[0:match_content.span()[0] + 1] + " " + expr[match_content.span()[0] + 1:]
-        match_content = re.search(search_string, expr)
-    # Remove space after prefix short forms if they are preceded by numbers, multiplication or space
-    # Example: "100 m Pa" ---> "100 mPa"
-    prefix_short_forms = "(" + "|".join(prefix_short_forms) + ")"
-    search_string = r"[0-9\*\(\) ]" + prefix_short_forms + " "
-    match_content = re.search(search_string, expr)
-    while match_content is not None:
-        expr = expr[0:match_content.span()[0] + 1] + match_content.group()[0:-1] + expr[match_content.span()[1]:]
-        match_content = re.search(search_string, expr)
-    # Remove multiplication and space after prefix short forms if they are preceded by numbers, multiplication or space
-    # Example:  "100 m* Pa" ---> "100 mPa"
-    search_string = r"[0-9\*\(\) ]" + prefix_short_forms + "\* "
-    match_content = re.search(search_string, expr)
-    while match_content is not None:
-        expr = expr[0:match_content.span()[0] + 1] + match_content.group()[0:-2] + expr[match_content.span()[1]:]
-        match_content = re.search(search_string, expr)
-    # Replace multiplication followed by space before unit short forms with only spaces if they are preceded by numbers or space
-    # Example:  "100* Pa" ---> "100 Pa"
-    unit_short_forms = "(" + "|".join(unit_short_forms) + ")"
-    search_string = r"[0-9\(\) ]\* " + unit_short_forms
-    match_content = re.search(search_string, expr)
-    while match_content is not None:
-        expr = expr[0:match_content.span()[0]] + match_content.group().replace("*", " ") + expr[
-                                                                                           match_content.span()[1]:]
-        match_content = re.search(search_string, expr)
-
-    return expr
-
-def transform_prefixes_to_standard(expr):
-    """
-    Transform ONLY alternative prefix spellings to standard prefix names.
-    Ensure there's exactly one space after the prefix before the unit.
-    Works for both attached (e.g. 'km') and spaced (e.g. 'k m') forms.
-    """
-
-    for prefix_name, symbol, power, alternatives in set_of_SI_prefixes:
-        for alt in alternatives:
-            if not alt:
-                continue
-
-            # Match the alternative prefix either attached to or followed by spaces before a unit
-            # Examples matched: "km", "k m", "microsecond", "micro second"
-            pattern = rf'(?<!\w){re.escape(alt)}\s*(?=[A-Za-zµΩ])'
-            expr = re.sub(pattern, prefix_name + ' ', expr)
-
-    # Normalize spacing (no multiple spaces)
-    expr = re.sub(r'\s{2,}', ' ', expr).strip()
-
-    return expr
-
-def expression_preprocess(name, expr, parameters):
-    if parameters.get("strictness", "natural") == "legacy":
-        expr = preprocess_legacy(expr, parameters)
-        return True, expr, None
-
-    expr = transform_prefixes_to_standard(expr)
-
-    return True, expr, None
-
 
 def feedback_string_generator(tags, graph, parameters_dict):
     strings = dict()

app/evaluation_tests.py

@@ -169,5 +169,29 @@ def test_multi_character_implicit_multi_variable(self):
         assert result["is_correct"] is True, "Response: a/bcd"
 
 
+    def test_mu_preview_evaluate(self):
+        response = "10 μA"
+        params = Params(is_latex=False, elementary_functions=False, strict_syntax=False, physical_quantity=True)
+        result = preview_function(response, params)
+        assert "preview" in result.keys()
+
+        preview = result["preview"]
+        assert preview["latex"] == "10~\\mathrm{microampere}"
+        assert preview["sympy"] == "10 μA"
+
+        params = {
+            "atol": 0.0,
+            "rtol": 0.0,
+            "strict_syntax": False,
+            "physical_quantity": True,
+            "elementary_functions": False,
+        }
+
+        response = preview["sympy"]
+        answer = "10 muA"
+        result = evaluation_function(response, answer, params)
+        assert result["is_correct"] is True
+
+
 if __name__ == "__main__":
     pytest.main(['-xk not slow', '--tb=short', '--durations=10', os.path.abspath(__file__)])

app/preview_implementations/physical_quantity_preview.py

@@ -16,7 +16,7 @@
 )
 
 from ..utility.expression_utilities import default_parameters as symbolic_default_parameters
-from ..utility.physical_quantity_utilities import SLR_quantity_parser as quantity_parser
+from ..utility.physical_quantity_utilities import SLR_quantity_parser as quantity_parser, expression_preprocess
 from ..utility.physical_quantity_utilities import SLR_quantity_parsing as quantity_parsing
 
 # CONSIDER: Move these to separate file so that they can be shared with
@@ -114,7 +114,8 @@ def preview_function(response: str, params: Params) -> Result:
             unit_sympy = res_parsed.unit.content_string() if unit is not None else ""
             sympy_out = value_sympy+separator_sympy+unit_sympy
         else:
-            res_parsed = quantity_parsing(response, params, parser, "response")
+            _, res_pre_processed, _ = expression_preprocess("response", response, params)
+            res_parsed = quantity_parsing(res_pre_processed, params, parser, "response")
             latex_out = res_parsed.latex_string
             sympy_out = response
 

app/preview_tests.py

@@ -93,7 +93,6 @@ def test_natural_logarithm_notation(self):
             ("e * x", True, False, "e * x", "E*x"),
             ("E", True, False, "E", "E",),
             ("ER_2", True, False, "ER_2", "E*R_2",),
-            # TODO: add exp (0), (1), (2) and (x)
             ("exp(1)", False, True, "e^{1}", "exp(1)"),
             ("e**1", False, True, "e^{1}", "E**1"),
             ("e^{1}", True, True, "e^{1}", "E"),

app/tests/physical_quantity_evaluation_tests.py

@@ -378,8 +378,8 @@ def test_answer_zero_value(self):
         "ans,res",
         [
             ("10 ohm", "10 Ω"),
-            ("10 micro A", "10 μA"),
-            ("10 micro A", "10 μ A"),
+            ("10 microA", "10 μA"),
+            ("10 microA", "10 μ A"),
             ("30 degree", "30 °"),
         ]
     )

app/utility/physical_quantity_utilities.py

@@ -273,6 +273,13 @@ def SLR_generate_unit_dictionaries(units_string, strictness):
                         prefixes_long_to_short[prefix]+units_long_to_short[unit]: prefix+units[unit]
                     }
                 )
+            if prefix + units_long_to_short[unit] not in units_short_to_long.keys():
+                prefixed_units.update(
+                    {
+                        prefix + units_long_to_short[unit]: prefix + units[unit]
+                    }
+                )
+
 
     prefixed_units_end = {**units_end}
     for unit in units_end.keys():
@@ -486,3 +493,104 @@ def SLR_quantity_parsing(expr, parameters, parser, name):
 
     tag_handler = set_tags(parameters.get("strictness", "strict"))
     return PhysicalQuantity(name, parameters, quantity[0], parser, messages=[], tag_handler=tag_handler)
+
+def expression_preprocess(name, expr, parameters):
+    if parameters.get("strictness", "natural") == "legacy":
+        expr = preprocess_legacy(expr, parameters)
+        return True, expr, None
+
+    expr = transform_prefixes_to_standard(expr)
+
+    return True, expr, None
+
+def preprocess_legacy(expr, parameters):
+    prefix_data = {(p[0], p[1], tuple(), p[3]) for p in set_of_SI_prefixes}
+    prefixes = []
+    for prefix in prefix_data:
+        prefixes = prefixes + [prefix[0]] + list(prefix[-1])
+    prefix_short_forms = [prefix[1] for prefix in prefix_data]
+    unit_data = set_of_SI_base_unit_dimensions \
+                | set_of_derived_SI_units_in_SI_base_units \
+                | set_of_common_units_in_SI \
+                | set_of_very_common_units_in_SI \
+                | set_of_imperial_units
+    unit_long_forms = prefixes
+    for unit in unit_data:
+        unit_long_forms = unit_long_forms + [unit[0]] + list(unit[-2]) + list(unit[-1])
+    unit_long_forms = "(" + "|".join(unit_long_forms) + ")"
+    # Rewrite any expression on the form "*UNIT" (but not "**UNIT") as " UNIT"
+    # Example: "newton*metre" ---> "newton metre"
+    search_string = r"(?<!\*)\* *" + unit_long_forms
+    match_content = re.search(search_string, expr[1:])
+    while match_content is not None:
+        expr = expr[0:match_content.span()[0] + 1] + match_content.group().replace("*", " ") + expr[
+                                                                                               match_content.span()[
+                                                                                                   1] + 1:]
+        match_content = re.search(search_string, expr[1:])
+    prefixes = "(" + "|".join(prefixes) + ")"
+    # Rewrite any expression on the form "PREFIX UNIT" as "PREFIXUNIT"
+    # Example: "kilo metre" ---> "kilometre"
+    search_string = prefixes + " " + unit_long_forms
+    match_content = re.search(search_string, expr)
+    while match_content is not None:
+        expr = expr[0:match_content.span()[0]] + " " + "".join(match_content.group().split()) + expr[
+                                                                                                match_content.span()[
+                                                                                                    1]:]
+        match_content = re.search(search_string, expr)
+    unit_short_forms = [u[1] for u in unit_data]
+    short_forms = "(" + "|".join(list(set(prefix_short_forms + unit_short_forms))) + ")"
+    # Add space before short forms of prefixes or unit names if they are preceded by numbers or multiplication
+    # Example: "100Pa" ---> "100 Pa"
+    search_string = r"[0-9\*\(\)]" + short_forms
+    match_content = re.search(search_string, expr)
+    while match_content is not None:
+        expr = expr[0:match_content.span()[0] + 1] + " " + expr[match_content.span()[0] + 1:]
+        match_content = re.search(search_string, expr)
+    # Remove space after prefix short forms if they are preceded by numbers, multiplication or space
+    # Example: "100 m Pa" ---> "100 mPa"
+    prefix_short_forms = "(" + "|".join(prefix_short_forms) + ")"
+    search_string = r"[0-9\*\(\) ]" + prefix_short_forms + " "
+    match_content = re.search(search_string, expr)
+    while match_content is not None:
+        expr = expr[0:match_content.span()[0] + 1] + match_content.group()[0:-1] + expr[match_content.span()[1]:]
+        match_content = re.search(search_string, expr)
+    # Remove multiplication and space after prefix short forms if they are preceded by numbers, multiplication or space
+    # Example:  "100 m* Pa" ---> "100 mPa"
+    search_string = r"[0-9\*\(\) ]" + prefix_short_forms + "\* "
+    match_content = re.search(search_string, expr)
+    while match_content is not None:
+        expr = expr[0:match_content.span()[0] + 1] + match_content.group()[0:-2] + expr[match_content.span()[1]:]
+        match_content = re.search(search_string, expr)
+    # Replace multiplication followed by space before unit short forms with only spaces if they are preceded by numbers or space
+    # Example:  "100* Pa" ---> "100 Pa"
+    unit_short_forms = "(" + "|".join(unit_short_forms) + ")"
+    search_string = r"[0-9\(\) ]\* " + unit_short_forms
+    match_content = re.search(search_string, expr)
+    while match_content is not None:
+        expr = expr[0:match_content.span()[0]] + match_content.group().replace("*", " ") + expr[
+                                                                                           match_content.span()[1]:]
+        match_content = re.search(search_string, expr)
+
+    return expr
+
+def transform_prefixes_to_standard(expr):
+    """
+    Transform ONLY alternative prefix spellings to standard prefix names.
+    Ensure there's exactly one space after the prefix before the unit.
+    Works for both attached (e.g. 'km') and spaced (e.g. 'k m') forms.
+    """
+
+    for prefix_name, symbol, power, alternatives in set_of_SI_prefixes:
+        for alt in alternatives:
+            if not alt:
+                continue
+
+            # Match the alternative prefix either attached to or followed by spaces before a unit
+            # Examples matched: "km", "k m", "microsecond", "micro second"
+            pattern = rf'(?<!\w){re.escape(alt)}\s*(?=[A-Za-zµΩ])'
+            expr = re.sub(pattern, prefix_name, expr)
+
+    # Normalize spacing (no multiple spaces)
+    expr = re.sub(r'\s{2,}', ' ', expr).strip()
+
+    return expr