Add files via upload

michalovadek · Oct 23, 2020 · 3239c0e · 3239c0e
1 parent b043911
commit 3239c0e
Show file tree

Hide file tree

Showing 5 changed files with 38 additions and 6 deletions.
diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,9 @@
+# eurlex 0.3.3
+
+## Minor changes
+
+- hotfix for critical bug in xml parsing that scrambled column with legal basis where this was requested
+
 # eurlex 0.3.2
 
 ## Major changes

diff --git a/R/elx_make_query.R b/R/elx_make_query.R
@@ -155,8 +155,7 @@ elx_make_query <- function(resource_type = c("directive","regulation","decision"
   ?type=<http://publications.europa.eu/resource/authority/resource-type/DEC_IMPL>||
   ?type=<http://publications.europa.eu/resource/authority/resource-type/DEC_DEL>||
   ?type=<http://publications.europa.eu/resource/authority/resource-type/DEC_FRAMW>||
-  ?type=<http://publications.europa.eu/resource/authority/resource-type/JOINT_DEC>||
-  ?type=<http://publications.europa.eu/resource/authority/resource-type/DEC_NC>)", sep = " ")
+  ?type=<http://publications.europa.eu/resource/authority/resource-type/JOINT_DEC>)", sep = " ")
   }
 
   if (resource_type == "caselaw"){

diff --git a/R/elx_parse_xml.R b/R/elx_parse_xml.R
@@ -19,9 +19,16 @@ elx_parse_xml <- function(sparql_response = ""){
   res_cols <- res_binding %>%
     xml2::xml_attr("name")
 
-  out <- data.frame(res_cols, res_text, stringsAsFactors = FALSE) %>%
-    dplyr::group_by(res_cols) %>%
-    dplyr::mutate(triplet = dplyr::row_number()) %>%
+  unique(res_cols)
+
+  out <- dplyr::tibble(res_cols, res_text) %>%
+    dplyr::mutate(is_work = ifelse(res_cols=="work", T, NA)) %>%
+    dplyr::group_by(is_work) %>%
+    dplyr::mutate(triplet = dplyr::row_number(),
+                  triplet = ifelse(is_work==T, triplet, NA)) %>%
+    dplyr::ungroup() %>%
+    tidyr::fill(triplet) %>%
+    dplyr::select(-.data$is_work) %>%
     tidyr::pivot_wider(names_from = res_cols, values_from = res_text) %>%
     dplyr::select(-.data$triplet)
 

diff --git a/README.md b/README.md
@@ -26,7 +26,7 @@ For the moment, it is recommended to retrieve metadata one variable at a time. F
 2. `dates <- elx_make_query("directive", include_date_transpos = TRUE) %>% elx_run_query()`
 3. `ids %>% dplyr::left_join(lbs) %>% dplyr::left_join(dates)`
 
-rather than `elx_make_query("directive", include_lbs = TRUE, include_date_transpos = TRUE)`. The reason is that observations with missing data on any variable are currently dropped entirely when cumulating variable requests. By separating the calls, you are able to at least identify the missing data.
+rather than `elx_make_query("directive", include_lbs = TRUE, include_date_transpos = TRUE)`. The reason is that rows with missing data on any variable are currently dropped entirely when cumulating variable requests. By separating the calls, you are able to identify the missing data, while retaining data from other columns.
 
 One of the main contributions of the SPARQL requests is that we obtain a comprehensive list of identifiers that we can subsequently use to obtain more data relating to the document in question. While the results of the SPARQL queries are useful also for webscraping (with the `rvest` package), the function `elx_fetch_data()` enables us to fire GET requests to retrieve data on documents with known identifiers (including Cellar URI). The function currently enables downloading the title and the full text of a document in all available languages.
 

diff --git a/eurlex.Rproj b/eurlex.Rproj
@@ -0,0 +1,20 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX
+
+AutoAppendNewline: Yes
+StripTrailingWhitespace: Yes
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source