feat: Generate stores taxonomy from name-suggestion-index #9607
+18,346
−0
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,298 @@ | ||
| // A nodejs script to parse NameSuggestionIndex formatted JSON data and attempt to output valid taxonomy data. | ||
| // Do not use results without careful review | ||
| const data = require('./supermarket.json'); | ||
|
|
||
| // A quick ISO 3601 to human labels (english) mapping. | ||
| // TODO: Ensure this matches exactly with countries.txt | ||
| // TODO: Replace with a better lookup | ||
|
Collaborator
There was a problem hiding this comment. Could this utilise the |
||
| var iso3601 = { | ||
| "ad": "Andorra", | ||
| "ae": "United Arab Emirates", | ||
| "af": "Afghanistan", | ||
| "ag": "Antigua & Barbuda", | ||
| "ai": "Anguilla", | ||
| "al": "Albania", | ||
| "am": "Armenia", | ||
| "an": "Netherlands Antilles", | ||
| "ao": "Angola", | ||
| "aq": "Antarctica", | ||
| "ar": "Argentina", | ||
| "as": "American Samoa", | ||
| "at": "Austria", | ||
| "au": "Australia", | ||
| "aw": "Aruba", | ||
| "az": "Azerbaijan", | ||
| "ba": "Bosnia & Herzegovina", | ||
| "bb": "Barbados", | ||
| "bd": "Bangladesh", | ||
| "be": "Belgium", | ||
| "bf": "Burkina Faso", | ||
| "bg": "Bulgaria", | ||
| "bh": "Bahrain", | ||
| "bi": "Burundi", | ||
| "bj": "Benin", | ||
| "bm": "Bermuda", | ||
| "bn": "Brunei Darussalam", | ||
| "bo": "Bolivia", | ||
| "br": "Brazil", | ||
| "bs": "Bahamas", | ||
| "bt": "Bhutan", | ||
| "bv": "Bouvet Island", | ||
| "bw": "Botswana", | ||
| "by": "Belarus", | ||
| "bz": "Belize", | ||
| "ca": "Canada", | ||
| "cc": "Cocos (Keeling) Islands", | ||
| "cd": "Zaire", | ||
| "cf": "Central African Republic", | ||
| "cg": "Congo", | ||
| "ch": "Switzerland", | ||
| "ci": "Cote D'ivoire (Ivory Coast)", | ||
| "ck": "Cook Islands", | ||
| "cl": "Chile", | ||
| "cm": "Cameroon", | ||
| "cn": "China", | ||
| "co": "Colombia", | ||
| "cr": "Costa Rica", | ||
| "cu": "Cuba", | ||
| "cv": "Cape Verde", | ||
| "cx": "Christmas Island", | ||
| "cy": "Cyprus", | ||
| "cz": "Czech Republic", | ||
| "de": "Germany", | ||
| "dj": "Djibouti", | ||
| "dk": "Denmark", | ||
| "dm": "Dominica", | ||
| "do": "Dominican Republic", | ||
| "dz": "Algeria", | ||
| "ec": "Ecuador", | ||
| "ee": "Estonia", | ||
| "eg": "Egypt", | ||
| "eh": "Western Sahara", | ||
| "er": "Eritrea", | ||
| "es": "Spain", | ||
| "et": "Ethiopia", | ||
| "fi": "Finland", | ||
| "fj": "Fiji", | ||
| "fk": "Falkland Islands (Malvinas)", | ||
| "fm": "Micronesia", | ||
| "fo": "Faroe Islands", | ||
| "fr": "France", | ||
| "ga": "Gabon", | ||
| "gb": "United Kingdom", | ||
| "gd": "Grenada", | ||
| "ge": "Georgia", | ||
| "gf": "French Guiana", | ||
| "gh": "Ghana", | ||
| "gi": "Gibraltar", | ||
| "gl": "Greenland", | ||
| "gm": "Gambia", | ||
| "gn": "Guinea", | ||
| "gp": "Guadeloupe", | ||
| "gq": "Equatorial Guinea", | ||
| "gr": "Greece", | ||
| "gs": "S.Georgia & S.Sandwich Islands", | ||
| "gt": "Guatemala", | ||
| "gu": "Guam", | ||
| "gw": "Guinea-Bissau", | ||
| "gy": "Guyana", | ||
| "hk": "Hong Kong", | ||
| "hm": "Heard & McDonald Islands", | ||
| "hn": "Honduras", | ||
| "hr": "Croatia (Hrvatska)", | ||
| "ht": "Haiti", | ||
| "hu": "Hungary", | ||
| "id": "Indonesia", | ||
| "ie": "Ireland", | ||
| "il": "Israel", | ||
| "in": "India", | ||
| "io": "British Indian Ocean Territory", | ||
| "iq": "Iraq", | ||
| "ir": "Iran", | ||
| "is": "Iceland", | ||
| "it": "Italy", | ||
| "jm": "Jamaica", | ||
| "jo": "Jordan", | ||
| "jp": "Japan", | ||
| "ke": "Kenya", | ||
| "kg": "Kyrgyzstan", | ||
| "kh": "Cambodia", | ||
| "ki": "Kiribati", | ||
| "km": "Comoros", | ||
| "kn": "Saint Kitts & Nevis", | ||
| "kp": "Korea (North)", | ||
| "kr": "Korea (South)", | ||
| "kw": "Kuwait", | ||
| "ky": "Cayman Islands", | ||
| "kz": "Kazakhstan", | ||
| "la": "Laos", | ||
| "lb": "Lebanon", | ||
| "lc": "Saint Lucia", | ||
| "li": "Liechtenstein", | ||
| "lk": "Sri Lanka", | ||
| "lr": "Liberia", | ||
| "ls": "Lesotho", | ||
| "lt": "Lithuania", | ||
| "lu": "Luxembourg", | ||
| "lv": "Latvia", | ||
| "ly": "Libya", | ||
| "ma": "Morocco", | ||
| "mc": "Monaco", | ||
| "md": "Moldova", | ||
| "mg": "Madagascar", | ||
| "mh": "Marshall Islands", | ||
| "mk": "Macedonia", | ||
| "ml": "Mali", | ||
| "mm": "Myanmar", | ||
| "mn": "Mongolia", | ||
| "mo": "Macau", | ||
| "mp": "Northern Mariana Islands", | ||
| "mq": "Martinique", | ||
| "mr": "Mauritania", | ||
| "ms": "Montserrat", | ||
| "mt": "Malta", | ||
| "mu": "Mauritius", | ||
| "mv": "Maldives", | ||
| "mw": "Malawi", | ||
| "mx": "Mexico", | ||
| "my": "Malaysia", | ||
| "mz": "Mozambique", | ||
| "na": "Namibia", | ||
| "nc": "New Caledonia", | ||
| "ne": "Niger", | ||
| "nf": "Norfolk Island", | ||
| "ng": "Nigeria", | ||
| "ni": "Nicaragua", | ||
| "nl": "Netherlands", | ||
| "no": "Norway", | ||
| "np": "Nepal", | ||
| "nr": "Nauru", | ||
| "nu": "Niue", | ||
| "nz": "New Zealand", | ||
| "om": "Oman", | ||
| "pa": "Panama", | ||
| "pe": "Peru", | ||
| "pf": "French Polynesia", | ||
| "pg": "Papua New Guinea", | ||
| "ph": "Philippines", | ||
| "pk": "Pakistan", | ||
| "pl": "Poland", | ||
| "pm": "St. Pierre & Miquelon", | ||
| "pn": "Pitcairn", | ||
| "pr": "Puerto Rico", | ||
| "pt": "Portugal", | ||
| "pw": "Palau", | ||
| "py": "Paraguay", | ||
| "qa": "Qatar", | ||
| "re": "Reunion", | ||
| "ro": "Romania", | ||
| "ru": "Russian Federation", | ||
| "rw": "Rwanda", | ||
| "sa": "Saudi Arabia", | ||
| "sb": "Solomon Islands", | ||
| "sc": "Seychelles", | ||
| "sd": "Sudan", | ||
| "se": "Sweden", | ||
| "sg": "Singapore", | ||
| "sh": "St. Helena", | ||
| "si": "Slovenia", | ||
| "sj": "Svalbard & Jan Mayen Islands", | ||
| "sk": "Slovak Republic", | ||
| "sl": "Sierra Leone", | ||
| "sm": "San Marino", | ||
| "sn": "Senegal", | ||
| "so": "Somalia", | ||
| "sr": "Suriname", | ||
| "st": "Sao Tome & Principe", | ||
| "sv": "El Salvador", | ||
| "sy": "Syria", | ||
| "sz": "Swaziland", | ||
| "tc": "Turks & Caicos Islands", | ||
| "td": "Chad", | ||
| "tf": "French Southern Territories", | ||
| "tg": "Togo", | ||
| "th": "Thailand", | ||
| "tj": "Tajikistan", | ||
| "tk": "Tokelau", | ||
| "tm": "Turkmenistan", | ||
| "tn": "Tunisia", | ||
| "to": "Tonga", | ||
| "tp": "East Timor", | ||
| "tr": "Turkey", | ||
| "tt": "Trinidad & Tobago", | ||
| "tv": "Tuvalu", | ||
| "tw": "Taiwan", | ||
| "tz": "Tanzania", | ||
| "ua": "Ukraine", | ||
| "ug": "Uganda", | ||
| "us": "United States of America", | ||
| "uy": "Uruguay", | ||
| "uz": "Uzbekistan", | ||
| "va": "Vatican City (Holy See)", | ||
| "vc": "St. Vincent & the Grenadines", | ||
| "ve": "Venezuela", | ||
| "vg": "Virgin Islands (British)", | ||
| "vi": "Virgin Islands (U.S.)", | ||
| "vn": "Viet Nam", | ||
| "vu": "Vanuatu", | ||
| "wf": "Wallis & Futuna Islands", | ||
| "ws": "Samoa", | ||
| "ye": "Yemen", | ||
| "yt": "Mayotte", | ||
| "yu": "Yugoslavia", | ||
| "za": "South Africa", | ||
| "zm": "Zambia", | ||
| "zw": "Zimbabwe", | ||
| "fx": "France (Metropolitan)" | ||
| } | ||
|
|
||
| // Overrides for the language codes/mappings inferred by country code. | ||
| // TODO: This list is far, far from accurate or complete and should be replaced with any internal/authoritative mappings | ||
|
Collaborator
There was a problem hiding this comment. Would it be possible to use the language property from the |
||
| var iso3601_to_language_mappings = { | ||
| "ca": "en", | ||
| "au": "en", | ||
| "us": "en", | ||
| "gb": "en" | ||
| }; | ||
|
|
||
| data["items"].forEach(function (record) { | ||
| var countryCodes = record.locationSet["include"]; | ||
| var countryNames = []; | ||
|
|
||
| const languageMatcher = /^(?<language>[a-z]{2})$/i; | ||
| const countryMatcher = /^(?<country>[a-z]{2})(?:-.+)?$/i; | ||
| countryCodes.forEach(function (code) { | ||
| if (code == "001" || typeof code !== 'string') { | ||
| console.debug("Incompatible code type", code, typeof code); | ||
| return; | ||
| } | ||
|
|
||
| const isoMatch = code.match(countryMatcher); | ||
| if (!iso3601[isoMatch?.groups?.country]) { | ||
| console.debug("Unmapped ISO3601 code", code, isoMatch); | ||
| return; | ||
| } else { | ||
| countryNames.push("en:" + iso3601[isoMatch.groups.country]); | ||
| } | ||
| }); | ||
|
|
||
| var primaryCountryCode = countryCodes[0].toString().split("-")[0]; | ||
| var primaryLanguageCode = primaryCountryCode; | ||
| if (iso3601_to_language_mappings[primaryCountryCode]) { | ||
| primaryLanguageCode = iso3601_to_language_mappings[primaryCountryCode] | ||
| } | ||
|
|
||
| if (!languageMatcher.test(primaryLanguageCode)) { | ||
| console.debug("Unmapped language code", primaryLanguageCode); | ||
| primaryLanguageCode = "xx"; | ||
| } | ||
|
|
||
| process.stdout.write([primaryLanguageCode, record.displayName].join(":") + "\n"); | ||
| if (record.tags["brand:wikidata"]) { | ||
| process.stdout.write(["wikidata:en", record.tags["brand:wikidata"]].join(":") + "\n"); | ||
| } | ||
| if (countryNames.length > 0) { | ||
| process.stdout.write(["country:en:", countryNames.join(",")].join(" ") + "\n"); | ||
| } | ||
| process.stdout.write("\n"); | ||
| }); | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm a big fan of the idea of leveraging NSI 👍
fyi I'm regularly contributing to the project, see openfoodfacts/open-prices#467 (comment)
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe store a
nsi_id: carrefour-c622afto know that it comes from NSI ?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Happy to split these out into an stores-nsi.txt or something of that nature to more clearly split it; I feel like at the time I did this manually.
Script likely needs to be re-run since it's been ~2 years.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I can have a look later this week and try to re-run the script myself.
if we switch to
xx:then the country mapping could be removed ?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think country mapping could still be useful, esp. for cases where store-brands may have identical or near-identical names in different regions (see e.g. the 50 or so “COOP”s). (Mappings like
country:en: en:United States of America,en:United States of America,en:United States of America,en:United States of America,en:United States of Americaare probably a bit excessive though…). Maybe this is too much “preemptive optimisation(/complication)” though, and could be easily solved with a human-addedcomment:en:key or similar where it’s actually needed.Definitely +1 to using
xx:similar to ourbrands.txttaxonomy though, with possible locale specific overrides for locales with scripts other than the first/primaryxx:alias where relevant.