Update to new UCUM version v2.2 (June-2024)

README.md

@@ -16,7 +16,7 @@ Note that UCUM does non provide a canonical representation, e.g. `m/s` and `m.s-
 
 - Parser for UCUM unit strings that implements the full grammar.
 - Converter for creating [pint](https://pypi.org/project/pint/) units from UCUM unit strings.
-- A pint unit definition file [pint_ucum_defs.txt](https://github.com/dalito/ucumvert/blob/main/src/ucumvert/pint_ucum_defs.txt) that extends pint´s default units with UCUM units. All UCUM units from Version 2.1 of the specification are included.
+- A pint unit definition file [pint_ucum_defs.txt](https://github.com/dalito/ucumvert/blob/main/src/ucumvert/pint_ucum_defs.txt) that extends pint´s default units with UCUM units. All UCUM units from the new version 2.2 of the specification (June 2024) are included.
 
 **ucumvert** generates the UCUM grammar by filling a template with unit codes, prefixes etc. from the official [ucum-essence.xml](https://github.com/ucum-org/ucum/blob/main/ucum-essence.xml) file (a copy is included in this repo).
 So updating the parser for new UCUM releases is straight forward.
@@ -126,7 +126,7 @@ To (re)generate this tsv-file from the official xlsx-file in the [UCUM repositor
 
 ```bash
 pip install openpyxl
-python src/src/ucumvert/vendor/get_ucum_example_as_tsv.py
+python src/ucumvert/vendor/get_ucum_example_as_tsv.py
 ```
 
 ## Useful links

src/ucumvert/parser.py

@@ -85,7 +85,7 @@
 #   instead of deca-r which does not exist.
 
 UCUM_GRAMMAR = """
-    # Based on UCUM specification (Version 2.1, 2017-11-21)
+    # Based on UCUM specification (Version 2.2, 2024-06-28)
     # Includes ucumvert-specific fixes to handle all common UCUM units
     # and some edge cases not present in the official examples.
     # This file is auto-created by parser.update_lark_ucum_grammar_file

src/ucumvert/pint_ucum_defs.txt

@@ -41,7 +41,7 @@ homeopathic_potency_of_quintamillesimal_korsakovian_series = 1 = _ = kp_Q
 high_power_field = 1 = _ = HPF
 low_power_field = 1 = _ = LPF
 international_unit = 1 = _ = i.U. = IU = iU
-arbitary_unit = 1 = _ = arb_U
+arbitrary_unit = 1 = _ = arb_U
 US_pharmacopeia_unit = 1 = _ = USP_U
 GPL_unit = 1 = _ = GPL_U
 MPL_unit = 1 = _ = MPL_U
@@ -88,6 +88,9 @@ diopter = 1 / meter = _ = diop
 slope = tan(1 rad)
 prism_diopter = 100 * tan(1 rad) = _ = p_diop
 
+nephelometric_turbidity_unit = 1 = _ = NTU
+formazin_nephelometric_unit = 1 = _ = FNU
+
 mil_i = inch / 1000
 cml_i = π/4 * mil_i**2
 hd_i = 4 * inch

src/ucumvert/pint_ucum_defs_mapping_report.txt

@@ -27,7 +27,7 @@
 #         Ti --> tebi (default registry)
 
 # === metric ===
-#        mol --> mole (default registry)                    # mol = 6.0221367 * 10*23  # METRIC, mole, amount of substance (si)
+#        mol --> mole (default registry)                    # mol = 6.02214076 * 10*23  # METRIC, mole, amount of substance (si)
 #         sr --> steradian (default registry)               # sr = 1 * rad2  # METRIC, steradian, solid angle (si)
 #         Hz --> hertz (default registry)                   # Hz = 1 * s-1  # METRIC, hertz, frequency (si)
 #          N --> newton (default registry)                  # N = 1 * kg.m/s2  # METRIC, newton, force (si)
@@ -53,18 +53,18 @@
 #         ar --> are (ucumvert registry)                    # ar = 100 * m2  # METRIC, are, area (iso1000)
 #          t --> metric_ton (default registry)              # t = 1e3 * kg  # METRIC, tonne, mass (iso1000)
 #        bar --> bar (default registry)                     # bar = 1e5 * Pa  # METRIC, bar, pressure (iso1000)
-#          u --> unified_atomic_mass_unit (default registry) # u = 1.6605402e-24 * g  # METRIC, unified atomic mass unit, mass (iso1000)
+#          u --> unified_atomic_mass_unit (default registry) # u = 1.66053906660e-24 * g  # METRIC, unified atomic mass unit, mass (iso1000)
 #         eV --> electron_volt (default registry)           # eV = 1 * [e].V  # METRIC, electronvolt, energy (iso1000)
 #         pc --> parsec (default registry)                  # pc = 3.085678e16 * m  # METRIC, parsec, length (iso1000)
 #        [c] --> speed_of_light (default registry)          # [c] = 299792458 * m/s  # METRIC, velocity of light, velocity (const)
-#        [h] --> planck_constant (default registry)         # [h] = 6.6260755e-34 * J.s  # METRIC, Planck constant, action (const)
-#        [k] --> boltzmann_constant (default registry)      # [k] = 1.380658e-23 * J/K  # METRIC, Boltzmann constant, (unclassified) (const)
+#        [h] --> planck_constant (default registry)         # [h] = 6.62607015e-34 * J.s  # METRIC, Planck constant, action (const)
+#        [k] --> boltzmann_constant (default registry)      # [k] = 1.380649e-23 * J/K  # METRIC, Boltzmann constant, (unclassified) (const)
 #    [eps_0] --> vacuum_permittivity (default registry)     # [eps_0] = 8.854187817e-12 * F/m  # METRIC, permittivity of vacuum, electric permittivity (const)
 #     [mu_0] --> vacuum_permeability (default registry)     # [mu_0] = 1 * 4.[pi].10*-7.N/A2  # METRIC, permeability of vacuum, magnetic permeability (const)
-#        [e] --> elementary_charge (default registry)       # [e] = 1.60217733e-19 * C  # METRIC, elementary charge, electric charge (const)
-#      [m_e] --> electron_mass (default registry)           # [m_e] = 9.1093897e-28 * g  # METRIC, electron mass, mass (const)
-#      [m_p] --> proton_mass (default registry)             # [m_p] = 1.6726231e-24 * g  # METRIC, proton mass, mass (const)
-#        [G] --> newtonian_constant_of_gravitation (default registry) # [G] = 6.67259e-11 * m3.kg-1.s-2  # METRIC, Newtonian constant of gravitation, (unclassified) (const)
+#        [e] --> elementary_charge (default registry)       # [e] = 1.602176634e-19 * C  # METRIC, elementary charge, electric charge (const)
+#      [m_e] --> electron_mass (default registry)           # [m_e] = 9.1093837139e-31 * kg  # METRIC, electron mass, mass (const)
+#      [m_p] --> proton_mass (default registry)             # [m_p] = 1.67262192595e-27 * kg  # METRIC, proton mass, mass (const)
+#        [G] --> newtonian_constant_of_gravitation (default registry) # [G] = 6.67430e-11 * m3.kg-1.s-2  # METRIC, Newtonian constant of gravitation, (unclassified) (const)
 #        [g] --> standard_gravity (default registry)        # [g] = 980665e-5 * m/s2  # METRIC, standard acceleration of free fall, acceleration (const)
 #       [ly] --> light_year (default registry)              # [ly] = 1 * [c].a_j  # METRIC, light-year, length (const)
 #         gf --> force_gram (default registry)              # gf = 1 * g.[g]  # METRIC, gram-force, force (const)
@@ -290,7 +290,7 @@
 #        [S] --> svedberg (default registry)                # [S] = 1 * 10*-13.s  # NON_METRIC, Svedberg unit, sedimentation coefficient (chemical)
 #      [HPF] --> high_power_field (ucumvert registry)       # [HPF] = 1 * 1  # NON_METRIC, high power field, view area in microscope (chemical)
 #      [LPF] --> low_power_field (ucumvert registry)        # [LPF] = 100 * 1  # NON_METRIC, low power field, view area in microscope (chemical)
-#    [arb'U] --> arbitary_unit (ucumvert registry)          # [arb'U] = 1 * 1  # NON_METRIC, arbitary unit, arbitrary (chemical)
+#    [arb'U] --> arbitrary_unit (ucumvert registry)         # [arb'U] = 1 * 1  # NON_METRIC, arbitrary unit, arbitrary (chemical)
 #    [USP'U] --> US_pharmacopeia_unit (ucumvert registry)   # [USP'U] = 1 * 1  # NON_METRIC, United States Pharmacopeia unit, arbitrary (chemical)
 #    [GPL'U] --> GPL_unit (ucumvert registry)               # [GPL'U] = 1 * 1  # NON_METRIC, GPL unit, biologic activity of anticardiolipin IgG (chemical)
 #    [MPL'U] --> MPL_unit (ucumvert registry)               # [MPL'U] = 1 * 1  # NON_METRIC, MPL unit, biologic activity of anticardiolipin IgM (chemical)
@@ -311,10 +311,10 @@
 #      [PFU] --> plaque_forming_unit (ucumvert registry)    # [PFU] = 1 * 1  # NON_METRIC, plaque forming units, amount of an infectious agent (chemical)
 #      [FFU] --> focus_forming_units (ucumvert registry)    # [FFU] = 1 * 1  # NON_METRIC, focus forming units, amount of an infectious agent (chemical)
 #      [CFU] --> colony_forming_unit (ucumvert registry)    # [CFU] = 1 * 1  # NON_METRIC, colony forming units, amount of a proliferating organism (chemical)
-#       [IR] --> allergene_index_of_reactivity (ucumvert registry) # [IR] = 1 * 1  # NON_METRIC, index of reactivity, amount of an allergen callibrated through in-vivo testing using the Stallergenes® method. (chemical)
-#      [BAU] --> bioequivalent_allergen_unit (ucumvert registry) # [BAU] = 1 * 1  # NON_METRIC, bioequivalent allergen unit, amount of an allergen callibrated through in-vivo testing based on the ID50EAL method of (intradermal dilution for 50mm sum of erythema diameters (chemical)
+#       [IR] --> allergene_index_of_reactivity (ucumvert registry) # [IR] = 1 * 1  # NON_METRIC, index of reactivity, amount of an allergen calibrated through in-vivo testing using the Stallergenes® method (chemical)
+#      [BAU] --> bioequivalent_allergen_unit (ucumvert registry) # [BAU] = 1 * 1  # NON_METRIC, bioequivalent allergen unit, amount of an allergen calibrated through in-vivo testing based on the ID50EAL method of (intradermal dilution for 50mm sum of erythema diameters (chemical)
 #       [AU] --> allergen_unit (ucumvert registry)          # [AU] = 1 * 1  # NON_METRIC, allergen unit, procedure defined amount of an allergen using some reference standard (chemical)
-# [Amb'a'1'U] --> allergen_unit_for_Ambrosia_artemisiifolia (ucumvert registry) # [Amb'a'1'U] = 1 * 1  # NON_METRIC, allergen unit for Ambrosia artemisiifolia, procedure defined amount of the major allergen of ragweed. (chemical)
+# [Amb'a'1'U] --> allergen_unit_for_Ambrosia_artemisiifolia (ucumvert registry) # [Amb'a'1'U] = 1 * 1  # NON_METRIC, allergen unit for Ambrosia artemisiifolia, procedure defined amount of the major allergen of ragweed (chemical)
 #      [PNU] --> protein_nitrogen_unit (ucumvert registry)  # [PNU] = 1 * 1  # NON_METRIC, protein nitrogen unit, procedure defined amount of a protein substance (chemical)
 #       [Lf] --> limit_of_flocculation (ucumvert registry)  # [Lf] = 1 * 1  # NON_METRIC, Limit of flocculation, procedure defined amount of an antigen substance (chemical)
 #   [D'ag'U] --> D_antigen_unit (ucumvert registry)         # [D'ag'U] = 1 * 1  # NON_METRIC, D-antigen unit, procedure defined amount of a poliomyelitis d-antigen substance (chemical)
@@ -324,11 +324,13 @@
 #         Ao --> angstrom (ucumvert registry)               # Ao = 0.1 * nm  # NON_METRIC, Ångström, length (misc)
 #          b --> barn (default registry)                    # b = 100 * fm2  # NON_METRIC, barn, action area (misc)
 #        att --> technical_atmosphere (ucumvert registry)   # att = 1 * kgf/cm2  # NON_METRIC, technical atmosphere, pressure (misc)
-#      [psi] --> pound_force_per_square_inch (default registry) # [psi] = 1 * [lbf_av]/[in_i]2  # NON_METRIC, pound per sqare inch, pressure (misc)
+#      [psi] --> pound_force_per_square_inch (default registry) # [psi] = 1 * [lbf_av]/[in_i]2  # NON_METRIC, pound per square inch, pressure (misc)
 #       circ --> turn (ucumvert registry)                   # circ = 2 * [pi].rad  # NON_METRIC, circle, plane angle (misc)
-#        sph --> sphere (ucumvert registry)                 # sph = 4 * [pi].sr  # NON_METRIC, spere, solid angle (misc)
+#        sph --> sphere (ucumvert registry)                 # sph = 4 * [pi].sr  # NON_METRIC, sphere, solid angle (misc)
 #    [car_m] --> carat (ucumvert registry)                  # [car_m] = 2e-1 * g  # NON_METRIC, metric carat, mass (misc)
 #   [car_Au] --> carat_of_gold_alloys (ucumvert registry)   # [car_Au] = 1/24  # NON_METRIC, carat of gold alloys, mass fraction (misc)
 #    [smoot] --> smoot (ucumvert registry)                  # [smoot] = 67 * [in_i]  # NON_METRIC, Smoot, length (misc)
 # [m/s2/Hz^(1/2)] --> meter_per_square_second_per_square_root_of_hertz (ucumvert registry) # [m/s2/Hz^(1/2)] = 1 * sqrt(1 m2/s4/Hz)  # NON_METRIC, meter per square seconds per square root of hertz, amplitude spectral density (misc)
+#      [NTU] --> nephelometric_turbidity_unit (ucumvert registry) # [NTU] = 1 * 1  # NON_METRIC, Nephelometric Turbidity Unit, turbidity (misc)
+#      [FNU] --> formazin_nephelometric_unit (ucumvert registry) # [FNU] = 1 * 1  # NON_METRIC, Formazin Nephelometric Unit, turbidity (misc)
 #      bit_s --> bit (ucumvert registry)                    # bit_s = 1 * ld(1 1)  # NON_METRIC, bit, amount of information (infotech)

src/ucumvert/ucum_grammar.lark

@@ -1,4 +1,4 @@
-# Based on UCUM specification (Version 2.1, 2017-11-21)
+# Based on UCUM specification (Version 2.2, 2024-06-28)
 # Includes ucumvert-specific fixes to handle all common UCUM units
 # and some edge cases not present in the official examples.
 # This file is auto-created by parser.update_lark_ucum_grammar_file
@@ -74,7 +74,8 @@ UNIT_NON_METRIC: "10*" |"10^" |"[pi]" |"%" |"[ppth]" |"[ppm]" |"[ppb]"
         |"[CCID_50]" |"[TCID_50]" |"[EID_50]" |"[PFU]" |"[FFU]" |"[CFU]"
         |"[IR]" |"[BAU]" |"[AU]" |"[Amb'a'1'U]" |"[PNU]" |"[Lf]" |"[D'ag'U]"
         |"[FEU]" |"[ELU]" |"[EU]" |"Ao" |"b" |"att" |"[psi]" |"circ" |"sph"
-        |"[car_m]" |"[car_Au]" |"[smoot]" |"[m/s2/Hz^(1/2)]" |"bit_s"
+        |"[car_m]" |"[car_Au]" |"[smoot]" |"[m/s2/Hz^(1/2)]" |"[NTU]"
+        |"[FNU]" |"bit_s"
 
 EXPONENT : ["+"|"-"] NON_ZERO_DIGITS
 FACTOR: NON_ZERO_DIGITS

src/ucumvert/ucum_pint.py

@@ -385,5 +385,6 @@ def run_examples():  # pragma: no cover
 
 
 if __name__ == "__main__":
-    run_examples()
-    # find_ucum_codes_that_need_mapping()
+    # run_examples()
+    find_matching_pint_definitions()
+    find_ucum_codes_that_need_mapping()

src/ucumvert/vendor/README.md

@@ -2,7 +2,7 @@
 
 This directory contain copies of files from the [UCUM repository](https://github.com/ucum-org/ucum) to enable running the code without internet access. The copied files fall under the [UCUM Copyright Notice and License](https://github.com/ucum-org/ucum/blob/main/LICENSE.md) (Version 1.0).
 
-* `ucum-essence.xml` - Version 2.1 (revision date: 2017-11-21 19:04:52 -0500).
+* `ucum-essence.xml` - Version 2.2 (revision date: 2024-06-17).
   * Used to build the terminals of the lark parser.
 * `ucum_examples.tsv` - Extracted from [TableOfExampleUcumCodesForElectronicMessaging.xlsx](https://github.com/ucum-org/ucum/blob/main/common-units/TableOfExampleUcumCodesForElectronicMessaging.xlsx), Version 1.5, released 06/2020
   * Used in unit tests. The tsv was created with the script `get_ucum_examples_as_tsv.py`.