From ec25367b9363c131f3b7443deef6cbd923894107 Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Thu, 3 Oct 2024 21:14:01 -0400 Subject: [PATCH 1/5] Add github action to codespell main on push and PRs --- .github/workflows/codespell.yml | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 .github/workflows/codespell.yml diff --git a/.github/workflows/codespell.yml b/.github/workflows/codespell.yml new file mode 100644 index 0000000..c59e047 --- /dev/null +++ b/.github/workflows/codespell.yml @@ -0,0 +1,25 @@ +# Codespell configuration is within .codespellrc +--- +name: Codespell + +on: + push: + branches: [main] + pull_request: + branches: [main] + +permissions: + contents: read + +jobs: + codespell: + name: Check for spelling errors + runs-on: ubuntu-latest + + steps: + - name: Checkout + uses: actions/checkout@v4 + - name: Annotate locations with typos + uses: codespell-project/codespell-problem-matcher@v1 + - name: Codespell + uses: codespell-project/actions-codespell@v2 From fab453a3d93862d458e9ebcca7b68b112f60e2f3 Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Thu, 3 Oct 2024 21:14:01 -0400 Subject: [PATCH 2/5] Add rudimentary codespell config --- .codespellrc | 7 +++++++ 1 file changed, 7 insertions(+) create mode 100644 .codespellrc diff --git a/.codespellrc b/.codespellrc new file mode 100644 index 0000000..5dd3797 --- /dev/null +++ b/.codespellrc @@ -0,0 +1,7 @@ +[codespell] +# Ref: https://github.com/codespell-project/codespell#using-a-config-file +skip = .git*,.codespellrc,*.cif +check-hidden = true +# lines with known to be non-english characters, all uppercase +ignore-regex = .*[úáüéè].*|\b[A-Z]+\b|\bvalue=".." +ignore-words-list = afe From a8db0c4b13908dd4b3caa002dea17b895f1843df Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Fri, 4 Oct 2024 11:26:21 -0400 Subject: [PATCH 3/5] [DATALAD RUNCMD] run codespell throughout fixing typos automagically (but ignoring overall fail due to ambigous ones) === Do not change lines below === { "chain": [], "cmd": "codespell -w || :", "exit": 0, "extra_inputs": [], "inputs": [], "outputs": [], "pwd": "." } ^^^ Do not change lines above ^^^ --- examples/pubchem/pubchem.xsd | 6 +++--- examples/ri.jsonld | 4 ++-- examples/ri_triples.txt | 2 +- examples/sections/framework_outline.jsonld | 2 +- examples/sections/procedure.jsonld | 2 +- ontology/cao.owl | 22 +++++++++++----------- ontology/chemical.owl | 2 +- ontology/scidata.owl | 14 +++++++------- ontology/scidata.ttl | 14 +++++++------- ontology/solubility.owl | 4 ++-- triples/ri_triples.txt | 2 +- 11 files changed, 37 insertions(+), 37 deletions(-) diff --git a/examples/pubchem/pubchem.xsd b/examples/pubchem/pubchem.xsd index 02a53ee..090c3b5 100644 --- a/examples/pubchem/pubchem.xsd +++ b/examples/pubchem/pubchem.xsd @@ -4814,7 +4814,7 @@ $Revision: 639093 $ measured end-points and parameters to be stored. An Assay Description is not a database table. You can define as many Result Definitions as needed and they need not be used by all Substances tested. Assay Descriptions can be modified on both description text and Result Definitions after initial submission - as desired, and such udpates will be tracked in PubChem + as desired, and such updates will be tracked in PubChem @@ -5542,7 +5542,7 @@ $Revision: 639093 $ - Mininum and Maximum Constraints on an Integer Value (used for validating incoming data) + Minimum and Maximum Constraints on an Integer Value (used for validating incoming data) @@ -5556,7 +5556,7 @@ $Revision: 639093 $ - Mininum and Maximum Constraints on a Real Value (used for validating incoming data) + Minimum and Maximum Constraints on a Real Value (used for validating incoming data) diff --git a/examples/ri.jsonld b/examples/ri.jsonld index 77b5bc1..112696c 100755 --- a/examples/ri.jsonld +++ b/examples/ri.jsonld @@ -159,8 +159,8 @@ }, { "@id": "chemical/2/", - "@type": "sdo:consituent", - "sourcetype": "commerical", + "@type": "sdo:constituent", + "sourcetype": "commercial", "name": "Hydrochloric acid", "source#": "substance/2/", "role#": "chm:solute", diff --git a/examples/ri_triples.txt b/examples/ri_triples.txt index d8abf95..0b5d23d 100644 --- a/examples/ri_triples.txt +++ b/examples/ri_triples.txt @@ -10,7 +10,7 @@ . . "Hydrochloric acid"^^ . - . + . "ACS Certified grade" . . . diff --git a/examples/sections/framework_outline.jsonld b/examples/sections/framework_outline.jsonld index f832b00..fb94e08 100755 --- a/examples/sections/framework_outline.jsonld +++ b/examples/sections/framework_outline.jsonld @@ -10,7 +10,7 @@ "@id": "identifier_(uri)", "uid": "unique identifier (string)", "title": "title (string)", - "authors": ["list of authors with e.g., affilation, email, ORCID"], + "authors": ["list of authors with e.g., affiliation, email, ORCID"], "description": "description (string)", "publisher": "publisher (string)", "keywords": "subject (string)", diff --git a/examples/sections/procedure.jsonld b/examples/sections/procedure.jsonld index c7ebde0..25e28d2 100755 --- a/examples/sections/procedure.jsonld +++ b/examples/sections/procedure.jsonld @@ -13,7 +13,7 @@ "title": "pH meter calibration", "description": "The pH electrode was calibrated at pH 7, pH 4, and pH 10 prior to measurement. A portion of the solution was transferred to a beaker and the DI water washed electrode wash placed in the solution and allowed to equilibrate before the measurement was taken", "scope": "measurement/1/", - "activity": "standarization", + "activity": "standardization", "sequence": { "@id": "sequence/", "@type": "afr:AFR_0000945", diff --git a/ontology/cao.owl b/ontology/cao.owl index f34fcf4..c03deec 100644 --- a/ontology/cao.owl +++ b/ontology/cao.owl @@ -657,7 +657,7 @@ Infrastructure category CAO_000003 - Information describing the people who are responsible for the analysis and place(s) where it occured + Information describing the people who are responsible for the analysis and place(s) where it occurred Person: Stuart Chalk @@ -910,7 +910,7 @@ Sample identifier - A string used to identifiy a sample + A string used to identify a sample CAO_000022 Person: Stuart Chalk @@ -1144,7 +1144,7 @@ Subsample identifier - A string used to identifiy a subsample + A string used to identify a subsample CAO_000041 Person: Stuart Chalk @@ -1392,7 +1392,7 @@ Chemometric datum CAO_000060 - Numeric value from a chemometric test peformed on data from a chemical analysis + Numeric value from a chemometric test performed on data from a chemical analysis Person: Stuart Chalk @@ -1936,7 +1936,7 @@ Datum property CAO_000102 - Charateristics of a numeric value + Characteristics of a numeric value Person: Stuart Chalk @@ -2228,7 +2228,7 @@ - Heterogenous mixture + Heterogeneous mixture A material where two or more substances and mixed together but the composition is different in different parts of the material CAO_000126 @@ -2409,7 +2409,7 @@ CAO_000140 Person: Stuart Chalk - Where a chemical entity acts as in interferring species in the detection of a chemical entity acting as an analyte + Where a chemical entity acts as in interfering species in the detection of a chemical entity acting as an analyte @@ -2675,7 +2675,7 @@ Numeric value - A representation of the numeric value of a dataum + A representation of the numeric value of a datum CAO_000161 Person: Stuart Chalk @@ -2989,7 +2989,7 @@ Replicate data - A group of data points that are nominally the same numeric value becuase they are equally valid estimates of a property of the same population, but due to random error will be scattered based on the distrubution model applicable in the context of process of measuring the data. + A group of data points that are nominally the same numeric value because they are equally valid estimates of a property of the same population, but due to random error will be scattered based on the distribution model applicable in the context of process of measuring the data. CAO_000184 Person: Stuart Chalk @@ -3131,7 +3131,7 @@ CAO_000195 Person: Stuart Chalk - Process of applying ultrasonic fequencies of sound to a solution in order to aid the process of dissolution + Process of applying ultrasonic frequencies of sound to a solution in order to aid the process of dissolution @@ -3182,7 +3182,7 @@ Standard method of analysis - A published standard method of chemical analysis that delineates sample processing, calibration, instrument setup, sample measurment, result calculation an method validation. Published by an organizational entity of high repute. + A published standard method of chemical analysis that delineates sample processing, calibration, instrument setup, sample measurement, result calculation an method validation. Published by an organizational entity of high repute. CAO_000199 Person: Stuart Chalk diff --git a/ontology/chemical.owl b/ontology/chemical.owl index 4eff69c..503b29b 100755 --- a/ontology/chemical.owl +++ b/ontology/chemical.owl @@ -331,7 +331,7 @@ obo:NCIT_C70848 - A distinctive alpha-numeric identification code assigned by the manufacturer or distributor to a specific quantity of manufactured material or product within a batch. + A distinctive alphanumeric identification code assigned by the manufacturer or distributor to a specific quantity of manufactured material or product within a batch. diff --git a/ontology/scidata.owl b/ontology/scidata.owl index 484909b..3b0b32a 100755 --- a/ontology/scidata.owl +++ b/ontology/scidata.owl @@ -2031,7 +2031,7 @@ bibo:doi - The digital object identifier - a unique identifer for digital assests. See http://doi.og + The digital object identifier - a unique identifier for digital assests. See http://doi.og @@ -2516,7 +2516,7 @@ #conversionFactor - A numeric multiplier used to convert a value in one unit of measure into another of the same quanity. Fo instance, the conversion factor for converting distance in miles to distances in meters is 1609.344. + A numeric multiplier used to convert a value in one unit of measure into another of the same quantity. Fo instance, the conversion factor for converting distance in miles to distances in meters is 1609.344. @@ -2716,7 +2716,7 @@ #dependent - The axis where a dependent varibale is plotted. + The axis where a dependent variable is plotted. @@ -2967,7 +2967,7 @@ #molecularSystem - A definition of an atom system used as a starting point for computational chemistry calculations. Typically atoms are defined at positions in three-dimensional space based on a particular co-ordinate system. Bonding between atoms may or may not be described. + A definition of an atom system used as a starting point for computational chemistry calculations. Typically atoms are defined at positions in three-dimensional space based on a particular coordinate system. Bonding between atoms may or may not be described. @@ -3169,7 +3169,7 @@ NOTE 3 In English, the terms for quantities in the left half of the table in 1.1 #quantityKind - quanity kind + quantity kind @@ -3274,7 +3274,7 @@ NOTE 3 In English, the terms for quantities in the left half of the table in 1.1 #siUnitEquivalent - SI unit that a derived or non-SI unit is equivalent to, for example the Joule has an equivlent SI unit of kg m2 s-2 + SI unit that a derived or non-SI unit is equivalent to, for example the Joule has an equivalent SI unit of kg m2 s-2 @@ -3629,7 +3629,7 @@ NOTE 3 In English, the terms for quantities in the left half of the table in 1.1 https://stuchalk.github.io/scidata/ontology/substance/substance.owl#substance - Also: A two or more chemicals interactive with each other, either the same or differnt states, at equilibirum or non-equilibrium with each other. This can be applied to all states and at all concentration levels. Generally the scope of chemical system extends to situations where the composition of the material is known. Complicated systems are better represented as materials. Examples include: gas mixtures, binary liquid mixtures, two immiscible liquids, gas/liquid equilibria, alloys, etc. + Also: A two or more chemicals interactive with each other, either the same or different states, at equilibirum or non-equilibrium with each other. This can be applied to all states and at all concentration levels. Generally the scope of chemical system extends to situations where the composition of the material is known. Complicated systems are better represented as materials. Examples include: gas mixtures, binary liquid mixtures, two immiscible liquids, gas/liquid equilibria, alloys, etc. diff --git a/ontology/scidata.ttl b/ontology/scidata.ttl index 6596a95..d70e9cd 100644 --- a/ontology/scidata.ttl +++ b/ontology/scidata.ttl @@ -580,7 +580,7 @@ dct:title rdf:type owl:Class ; ### http://purl.org/ontology/bibo/doi bibo:doi rdf:type owl:Class ; rdfs:subClassOf :metadata ; - obo:IAO_0000115 "The digital object identifier - a unique identifer for digital assests. See http://doi.og" ; + obo:IAO_0000115 "The digital object identifier - a unique identifier for digital assests. See http://doi.og" ; oboowl:id "doi" ; rdfs:label "doi" . @@ -835,7 +835,7 @@ foaf:organization rdf:type owl:Class ; ### https://stuchalk.github.io/scidata/ontology/scidata#conversionFactor :conversionFactor rdf:type owl:Class ; rdfs:subClassOf :unitOfMeasurement ; - obo:IAO_0000115 "A numeric multiplier used to convert a value in one unit of measure into another of the same quanity. Fo instance, the conversion factor for converting distance in miles to distances in meters is 1609.344." ; + obo:IAO_0000115 "A numeric multiplier used to convert a value in one unit of measure into another of the same quantity. Fo instance, the conversion factor for converting distance in miles to distances in meters is 1609.344." ; oboowl:id "conversionFactor" ; rdfs:label "conversion factor" . @@ -1056,7 +1056,7 @@ foaf:organization rdf:type owl:Class ; ### https://stuchalk.github.io/scidata/ontology/scidata#molecularSystem :molecularSystem rdf:type owl:Class ; rdfs:subClassOf :systemFacet ; - obo:IAO_0000115 "A definition of an atom system used as a starting point for computational chemistry calculations. Typically atoms are defined at positions in three-dimensional space based on a particular co-ordinate system. Bonding between atoms may or may not be described." ; + obo:IAO_0000115 "A definition of an atom system used as a starting point for computational chemistry calculations. Typically atoms are defined at positions in three-dimensional space based on a particular coordinate system. Bonding between atoms may or may not be described." ; oboowl:id "molecularSystem" ; rdfs:label "molecular system" . @@ -1161,7 +1161,7 @@ EXAMPLE The quantities moment of force and energy are, by convention, not regard NOTE 3 In English, the terms for quantities in the left half of the table in 1.1, Note 1, are often used for the corresponding 'kinds of quantity'. In French, the term “nature” is only used in expressions such as “grandeurs de même nature” (in English, “quantities of the same kind”)."""@en ; obo:IAO_0000119 "International Vocabulary of Metrology - Online Edition, https://jcgm.bipm.org/vim/en/1.2.html"@en ; oboowl:hasExactSynonym "kind of quantity"@en ; - rdfs:label "quanity kind"@en . + rdfs:label "quantity kind"@en . ### https://stuchalk.github.io/scidata/ontology/scidata#resource @@ -1222,7 +1222,7 @@ NOTE 3 In English, the terms for quantities in the left half of the table in 1.1 ### https://stuchalk.github.io/scidata/ontology/scidata#siUnitEquivalent :siUnitEquivalent rdf:type owl:Class ; rdfs:subClassOf :unitOfMeasurement ; - obo:IAO_0000115 "SI unit that a derived or non-SI unit is equivalent to, for example the Joule has an equivlent SI unit of kg m2 s-2" ; + obo:IAO_0000115 "SI unit that a derived or non-SI unit is equivalent to, for example the Joule has an equivalent SI unit of kg m2 s-2" ; oboowl:id "siUnitEquivalent" ; rdfs:label "SI unit equivalent" . @@ -1399,7 +1399,7 @@ NOTE 3 In English, the terms for quantities in the left half of the table in 1.1 obo:IAO_0000115 "Matter of constant composition best characterized by the entities (molecules, formula units, atoms) it is composed of. Physical properties such as density, refractive index, electric conductivity, melting point etc. characterize the chemical substance." ; oboowl:hasExactSynonym "chemical substance" ; oboowl:id "substance" ; - rdfs:comment "Also: A two or more chemicals interactive with each other, either the same or differnt states, at equilibirum or non-equilibrium with each other. This can be applied to all states and at all concentration levels. Generally the scope of chemical system extends to situations where the composition of the material is known. Complicated systems are better represented as materials. Examples include: gas mixtures, binary liquid mixtures, two immiscible liquids, gas/liquid equilibria, alloys, etc." ; + rdfs:comment "Also: A two or more chemicals interactive with each other, either the same or different states, at equilibirum or non-equilibrium with each other. This can be applied to all states and at all concentration levels. Generally the scope of chemical system extends to situations where the composition of the material is known. Complicated systems are better represented as materials. Examples include: gas mixtures, binary liquid mixtures, two immiscible liquids, gas/liquid equilibria, alloys, etc." ; rdfs:isDefinedBy ; rdfs:label "substance" . @@ -1411,7 +1411,7 @@ NOTE 3 In English, the terms for quantities in the left half of the table in 1.1 ### https://stuchalk.github.io/scidata/ontology/scidata#dependent :dependent rdf:type owl:NamedIndividual , :axisType ; - obo:IAO_0000115 "The axis where a dependent varibale is plotted." ; + obo:IAO_0000115 "The axis where a dependent variable is plotted." ; rdfs:label "dependent" . diff --git a/ontology/solubility.owl b/ontology/solubility.owl index ef1a3f2..4dfeeb1 100755 --- a/ontology/solubility.owl +++ b/ontology/solubility.owl @@ -240,7 +240,7 @@ In ternary and higher-order systems, composition below or above which, on a tern #SO_000007 - Activity Coefficent at Infinite Dilution + Activity Coefficient at Infinite Dilution @@ -305,7 +305,7 @@ https://en.wikipedia.org/wiki/Henry's_law#Henry's_law_volatility_const #SO_000011 - Thisis placeholder for IUPAC defintion + Thisis placeholder for IUPAC definition diff --git a/triples/ri_triples.txt b/triples/ri_triples.txt index 5f998b9..f3aacca 100755 --- a/triples/ri_triples.txt +++ b/triples/ri_triples.txt @@ -10,7 +10,7 @@ "MilliQ Grade (18.2 MOhms)" . . "Hydrochloric acid"^^ . - . + . "chm:solute"^^ . . "ACS Certified grade" . From 2326e078f68980b5eee2d71e65cc105c0d3c828f Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Mon, 7 Oct 2024 11:39:26 -0400 Subject: [PATCH 4/5] [DATALAD RUNCMD] Do interactive fixing of some ambigous typos === Do not change lines below === { "chain": [], "cmd": "codespell -w -i 3 -C 2", "exit": 0, "extra_inputs": [], "inputs": [], "outputs": [], "pwd": "." } ^^^ Do not change lines above ^^^ --- examples/sections/framework_outline.jsonld | 2 +- ontology/cao.owl | 4 ++-- ontology/scidata.owl | 4 ++-- ontology/scidata.ttl | 4 ++-- schema/molsystem.json | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/examples/sections/framework_outline.jsonld b/examples/sections/framework_outline.jsonld index fb94e08..cc77449 100755 --- a/examples/sections/framework_outline.jsonld +++ b/examples/sections/framework_outline.jsonld @@ -17,7 +17,7 @@ "version": "version of the data not the file (integer)", "permalink": "permanent URL to file (uri)", "related": ["one or more external links related to this file (uri)"], - "toc": ["links sections of this file (interal uri)"], + "toc": ["links sections of this file (internal uri)"], "ids": ["links to ontology defined terms (external uri)"], "scidata": { "@id": "scidataFramework/", diff --git a/ontology/cao.owl b/ontology/cao.owl index c03deec..9c64e47 100644 --- a/ontology/cao.owl +++ b/ontology/cao.owl @@ -1427,7 +1427,7 @@ Sample spike recovery percentage - Analysis of a sample spiked with a known amount of analyte. The result is compared to the analysis portion of the same sample and the different is compared to the amount of analyte added. If the difference in the results is equivalent ot the amount added then the recovery is deemed 100%. + Analysis of a sample spiked with a known amount of analyte. The result is compared to the analysis portion of the same sample and the different is compared to the amount of analyte added. If the difference in the results is equivalent to the amount added then the recovery is deemed 100%. CAO_000063 Person: Stuart Chalk @@ -2601,7 +2601,7 @@ CAO_000155 Method of standard addition Person: Stuart Chalk - Process by which calibration is performed on a sample where the matrix components cause the signal from the analyte to be enchanced or deminished by the 'matrix effect'. The same small portion of a sample is added to all calibration solutions so that the matrix is matched, and the analyte concentration is determined by extrapolation of the regression line to y=0. + Process by which calibration is performed on a sample where the matrix components cause the signal from the analyte to be enhanced or deminished by the 'matrix effect'. The same small portion of a sample is added to all calibration solutions so that the matrix is matched, and the analyte concentration is determined by extrapolation of the regression line to y=0. Standard additions calibration Statistics and Chemometrics for Analytical Chemistry, 6th Ed. 2010 Miller and Miller ISBN 978-0273730422 p128 diff --git a/ontology/scidata.owl b/ontology/scidata.owl index 3b0b32a..55ddb04 100755 --- a/ontology/scidata.owl +++ b/ontology/scidata.owl @@ -2376,7 +2376,7 @@ #axisType - Wether a dataseries in the independent or dependent axis of a chart + Whether a dataseries in the independent or dependent axis of a chart @@ -2516,7 +2516,7 @@ #conversionFactor - A numeric multiplier used to convert a value in one unit of measure into another of the same quantity. Fo instance, the conversion factor for converting distance in miles to distances in meters is 1609.344. + A numeric multiplier used to convert a value in one unit of measure into another of the same quantity. For instance, the conversion factor for converting distance in miles to distances in meters is 1609.344. diff --git a/ontology/scidata.ttl b/ontology/scidata.ttl index d70e9cd..68200e6 100644 --- a/ontology/scidata.ttl +++ b/ontology/scidata.ttl @@ -756,7 +756,7 @@ foaf:organization rdf:type owl:Class ; ### https://stuchalk.github.io/scidata/ontology/scidata#axisType :axisType rdf:type owl:Class ; rdfs:subClassOf :dataset ; - obo:IAO_0000115 "Wether a dataseries in the independent or dependent axis of a chart" ; + obo:IAO_0000115 "Whether a dataseries in the independent or dependent axis of a chart" ; oboowl:id "axisType" ; rdfs:label "axis type" . @@ -835,7 +835,7 @@ foaf:organization rdf:type owl:Class ; ### https://stuchalk.github.io/scidata/ontology/scidata#conversionFactor :conversionFactor rdf:type owl:Class ; rdfs:subClassOf :unitOfMeasurement ; - obo:IAO_0000115 "A numeric multiplier used to convert a value in one unit of measure into another of the same quantity. Fo instance, the conversion factor for converting distance in miles to distances in meters is 1609.344." ; + obo:IAO_0000115 "A numeric multiplier used to convert a value in one unit of measure into another of the same quantity. For instance, the conversion factor for converting distance in miles to distances in meters is 1609.344." ; oboowl:id "conversionFactor" ; rdfs:label "conversion factor" . diff --git a/schema/molsystem.json b/schema/molsystem.json index 8355866..6c04191 100644 --- a/schema/molsystem.json +++ b/schema/molsystem.json @@ -86,7 +86,7 @@ }, "atom": { "type": "array", - "itmes": { + "items": { "type": "object", "properties": { "@id": { "type": "string" }, From 1286de03ac2c6a1d2b7ffd466043feaa45d47657 Mon Sep 17 00:00:00 2001 From: Yaroslav Halchenko Date: Tue, 15 Oct 2024 10:39:13 -0400 Subject: [PATCH 5/5] Manual fix of a spotted typo Thisis --- ontology/solubility.owl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ontology/solubility.owl b/ontology/solubility.owl index 4dfeeb1..edce1c1 100755 --- a/ontology/solubility.owl +++ b/ontology/solubility.owl @@ -305,7 +305,7 @@ https://en.wikipedia.org/wiki/Henry's_law#Henry's_law_volatility_const #SO_000011 - Thisis placeholder for IUPAC definition + This is a placeholder for IUPAC definition