Add spanish regex

R/codelist.R

@@ -1,6 +1,6 @@
 #' Country Code Translation Data Frame (Cross-Sectional)
 #'
 #' A data frame used internally by the [countrycode()] function. `countrycode` can use any valid code as destination, but only some codes can be used as origin.
 #'
 #' ## Origin and Destination
 #'
@@ -9,12 +9,13 @@
 #' - `country.name.de`: country name (German)
 #' - `country.name.fr`: country name (French)
 #' - `country.name.it`: country name (Italian)
+#' - `country.name.es`: country name (Spanish)
 #' - `cowc`: Correlates of War character
 #' - `cown`: Correlates of War numeric
 #' - `dhs`: Demographic and Health Surveys Program
 #' - `ecb`: European Central Bank
 #' - `eurostat`:  Eurostat
 #' - `fao`: Food and Agriculture Organization of the United Nations numerical code
 #' - `fips`: FIPS 10-4 (Federal Information Processing Standard)
 #' - `gaul`: Global Administrative Unit Layers
 #' - `genc2c`: GENC 2-letter code
@@ -22,7 +23,7 @@
 #' - `genc3n`: GENC numeric code
 #' - `gwc`: Gleditsch & Ward character
 #' - `gwn`: Gleditsch & Ward numeric
 #' - `imf`: International Monetary Fund (Warning: The IMF generally uses ISO codes. These codes are WEO-related, but may be inconsistently used in the wild.)
 #' - `ioc`: International Olympic Committee
 #' - `iso2c`: ISO-2 character
 #' - `iso3c`: ISO-3 character
@@ -41,8 +42,8 @@
 #'
 #' ## Destination only
 #'
 #' - `cldr.*`: 600+ country name variants from the UNICODE CLDR project (e.g., "cldr.short.en").
 #'   Inspect the [`cldr_examples`][countrycode::cldr_examples] data.frame for a full list of
 #'   available country names and examples.
 #' - `ar5`: IPCC's regional mapping used both in the Fifth Assessment Report
 #'              (AR5) and for the Reference Concentration Pathways (RCP)
@@ -50,7 +51,7 @@
 #' - `cow.name`: Correlates of War country name
 #' - `currency`: ISO 4217 currency name
 #' - `eurocontrol_pru`:  European Organisation for the Safety of Air Navigation
 #' - `eurocontrol_statfor`:  European Organisation for the Safety of Air Navigation
 #' - `eu28`: Member states of the European Union (as of December 2015),
 #'               without special territories
 #' - `icao.region`: International Civil Aviation Organization region
@@ -60,7 +61,7 @@
 #' - `iso4217n`: ISO 4217 currency numeric code
 #' - `p4.name`: Polity IV country name
 #' - `region`: 7 Regions as defined in the World Bank Development Indicators
 #' - `region23`: 23 Regions as used to be in the World Bank Development Indicators (legacy)
 #' - `telephone`: ITU-T E.164 country codes for telecommunication
 #' - `un.name.ar`: United Nations Arabic country name
 #' - `un.name.en`: United Nations English country name
@@ -83,7 +84,7 @@
 #' conversion dictionary, this forces us to make arbitrary choices with respect
 #' to some entities (e.g., Western Germany, Vietnam, Serbia). `countrycode`
 #' includes a reconciled dataset in panel format,
 #' [`codelist_panel`][countrycode::codelist_panel]. Instead of converting code, we recommend
 #' that users dealing with panel data "left-merge" their data into this panel
 #' dictionary.
 #'

R/countrycode.R

@@ -19,12 +19,12 @@
 #' [`codelist_panel`][codelist_panel] data.frame as a base into which they can
 #' merge their other data. This data.frame includes most relevant code, and is
 #' already "reconciled" to ensure that each political unit is only represented
 #' by one row in any given year. From there, it is just a matter of using [merge()]
 #' to combine different datasets which use different codes.
 #'
 #' @param sourcevar Vector which contains the codes or country names to be
 #'   converted (character or factor)
 #' @param origin A string which identifies the coding scheme of origin (e.g., `"iso3c"`). See
 #'   [`codelist`][codelist] for a list of available codes.
 #' @param destination A string or vector of strings which identify the coding
 #'   scheme of destination (e.g., `"iso3c"` or `c("cowc", "iso3c")`). See
@@ -101,11 +101,13 @@
             "genc2c", "genc3c", "genc3n", "gwc", "gwn", "imf", "ioc", "iso2c",
             "iso3c", "iso3n", "p5c", "p5n", "p4c", "p4n", "un", "un_m49", "unicode.symbol",
             "unhcr", "unpd", "vdem", "wb", "wb_api2c", "wb_api3c", "wvs",
-            "country.name.en.regex", "country.name.de.regex", "country.name.fr.regex", "country.name.it.regex")
+            "country.name.en.regex", "country.name.de.regex", "country.name.fr.regex",
+            "country.name.it.regex", "country.name.es.regex")
         attr(dictionary, "origin_regex") <- c("country.name.de.regex",
                                               "country.name.en.regex",
                                               "country.name.fr.regex",
-                                              "country.name.it.regex")
+                                              "country.name.it.regex",
+                                              "country.name.es.regex")
     } else {
         dictionary <- custom_dict
     }
@@ -115,7 +117,7 @@
         if (origin == 'country.name') {
             origin <- 'country.name.en'
         }
-        if (origin %in% c('country.name.en', 'country.name.de', 'country.name.it', 'country.name.fr')) {
+        if (origin %in% c('country.name.en', 'country.name.de', 'country.name.it', 'country.name.fr', 'country.name.es')) {
             origin <- paste0(origin, '.regex')
         }
         destination[destination == "country.name"] <- 'country.name.en'

tests/testthat/test-corner-cases.R

@@ -112,6 +112,9 @@ test_that("netherlands", {
     expect_equal(
         countrycode("Caraibi olandesi", "country.name.it", "country.name.en"),
         "Caribbean Netherlands")
+    expect_equal(
+      countrycode("Caribe holandes", "country.name.es", "country.name.en"),
+      "Netherlands Antilles")
 })
 
 

tests/testthat/test-regex-internal.R

@@ -23,6 +23,11 @@ test_that("Italian regex vs. CLDR", {
     expect_equal(x, codelist$cldr.name.it)
 })
 
+test_that("Spanish regex vs. CLDR", {
+  x <- countrycode(codelist$cldr.name.es, "country.name.es", "cldr.name.es")
+  expect_equal(x, codelist$cldr.name.es)
+})
+
 test_that("German regex vs. CLDR", {
     x <- countrycode(codelist$cldr.name.de, "country.name.de", "cldr.name.de")
     expect_equal(x, codelist$cldr.name.de)
@@ -33,4 +38,21 @@ test_that("French regex vs. CLDR", {
     expect_equal(x, codelist$cldr.name.fr)
 })
 
+test_that("Spanish regex vs. CLDR 419", {
+  x <- countrycode(codelist$cldr.name.es_419, "country.name.es", "cldr.name.es_419")
+  expect_equal(x, codelist$cldr.name.es_419)
+})
 
+test_that("Spanish regex vs. CLDR short", {
+  x <- countrycode(codelist$cldr.short.es, "country.name.es", "cldr.short.es")
+  expect_equal(x, codelist$cldr.short.es)
+})
+
+test_that("Spanish regex vs. CLDR variant", {
+  x <- countrycode(codelist$cldr.variant.es, "country.name.es", "cldr.variant.es")
+  expect_equal(x, codelist$cldr.variant.es)
+})
+test_that("Spanish regex vs. UN", {
+  x <- countrycode(codelist$un.name.es, "country.name.es", "un.name.es")
+  expect_equal(x, codelist$un.name.es)
+})

tests/testthat/test-regex-special.R

@@ -141,6 +141,7 @@ test_that('Micronesia is not Federated States of Micronesia', {
     expect_equal(countrycode('Mikronesien', 'country.name.de', 'iso3c', warn = FALSE), NA_character_)
     expect_equal(countrycode('Micron\u00e9sie', 'country.name.fr', 'iso3c', warn = FALSE), NA_character_)
     expect_equal(countrycode('Micronesia', 'country.name.it', 'iso3c', warn = FALSE), NA_character_)
+    expect_equal(countrycode('Micronesia', 'country.name.es', 'iso3c', warn = FALSE), NA_character_)
     # unambiguous full English names → FSM
     expect_equal(iso3c_of('Federated States of Micronesia'), 'FSM')
     expect_equal(iso3c_of('Micronesia, Federated States of'), 'FSM')
@@ -162,6 +163,10 @@ test_that('Micronesia is not Federated States of Micronesia', {
     expect_equal(countrycode('Stati Federati di Micronesia', 'country.name.it', 'iso3c'), 'FSM')
     expect_equal(countrycode('Micronesia (Stati Federati di)', 'country.name.it', 'iso3c'), 'FSM')
     expect_equal(countrycode('FS Micronesia', 'country.name.it', 'iso3c'), 'FSM')
+    # Spanish: qualified forms → FSM, FS abbreviation → FSM
+    expect_equal(countrycode('Estados Federados de Micronesia', 'country.name.es', 'iso3c'), 'FSM')
+    expect_equal(countrycode('Micronesia (Estados Federados de)', 'country.name.es', 'iso3c'), 'FSM')
+    expect_equal(countrycode('FS Micronesia', 'country.name.es', 'iso3c'), 'FSM')
 })