add documentation for read_from_csv_or_fetch

NAMESPACE

@@ -7,6 +7,7 @@ export(join_speaker)
 export(party_colors)
 export(read_all)
 export(read_from_csv)
+export(read_from_csv_or_fetch)
 export(repair)
 export(word_usage_by_date)
 export(write_to_csv)

R/fetch.R

@@ -61,10 +61,3 @@ fetch_all <- function(download_dir="inst/records/", create=FALSE) {
     # if successful, set progressbar to 100%
     setTimerProgressBar(pb, 250)
 }
-
-stop_dir_not_creatable <- function(cond) {
-    # currently this has call: dir.create(download_dir)
-    # do we want to change this to fetch_all(...) ?
-    cond$message <- "Directory does not exist and can't be created. Probably because the path is not writeable."
-    stop(cond)
-}

R/helpers.R

@@ -19,6 +19,13 @@ check_directory <- function(path, create=F) {
     }
 }
 
+stop_dir_not_creatable <- function(cond) {
+    # currently this has call: dir.create(download_dir)
+    # do we want to change this to fetch_all(...) ?
+    cond$message <- "Directory does not exist and can't be created. Probably because the path is not writeable."
+    stop(cond)
+}
+
 # appends a file seperator at end of path if needed
 make_directory_path <- function(path) {
     if (!str_ends(path, .Platform$file.sep)) str_c(path, .Platform$file.sep)

R/parse.R

@@ -233,6 +233,11 @@ parse_speakerlist <- function(speakerliste_xml) {
 #' 
 #' @export
 write_to_csv <- function(tables, path="inst/csv/", create=F) {
+    is_valid_res(tables)
+    stopifnot("path must be of type character" = is.character(path))
+    stopifnot("create must be of type logical" = is.logical(create))
+
+    path <- make_directory_path(path)
     check_directory(path, create)
     write.table(tables$speaker, str_c(path, "speaker.csv"))
     write.table(tables$speeches, str_c(path, "speeches.csv"))
@@ -250,6 +255,9 @@ write_to_csv <- function(tables, path="inst/csv/", create=F) {
 #' 
 #' @export
 read_from_csv <- function(path="inst/csv/") {
+    stopifnot("path must be of type character" = is.character(path))
+
+    path <- make_directory_path(path)
     list(speaker = read.table(str_c(path, "speaker.csv")) %>%
              tibble() %>%
              mutate(id = as.character(id)),
@@ -259,5 +267,26 @@ read_from_csv <- function(path="inst/csv/") {
                     date = as.Date(date)),
          talks = tibble %$% read.table(str_c(path, "talks.csv")),
          comments = tibble %$% read.table(str_c(path, "comments.csv")),
-         applause = tibble %$% read.table(str_c(path, "applause.csv")))
+         applause = tibble %$% read.table(str_c(path, "applause.csv"))) -> res
+    is_valid_res(res)
+    res
+}
+
+#' @param path directory of csv files to read
+#' read data from csv files if they exist already
+#' otherwise fetch protocols and then write the data into csv files
+#' 
+#' @export
+read_from_csv_or_fetch <- function(path="inst/") {
+    path <- make_directory_path(path)
+    res <- tryCatch(read_from_csv(str_c(path, "csv/")),
+                    error = function(c) NULL)
+    if (!is.null(res)) return(res)
+    
+    fetch_all(str_c(path, "records/"), create=T)
+    read_all(str_c(path, "records/")) %>%
+        repair() ->
+        res
+    write_to_csv(res, str_c(path, "csv/"), create=T)
+    res
 }

README.md

@@ -9,6 +9,7 @@ Using the `remotes` package, this is easily installed via:
 ```r
 remotes::install_url("https://git.flavigny.de/christian/hateimparlament/archive/master.zip")
 ```
+If you want to build the vignettes, pass `build_vignettes = TRUE`.
 
 # Features
 

vignettes/explicittopic.Rmd

@@ -1,8 +1,8 @@
 ---
-title: "explicittopic"
+title: "Analysis of covered topics"
 output: rmarkdown::html_vignette
 vignette: >
-  %\VignetteIndexEntry{explicittopic}
+  %\VignetteIndexEntry{Analysis of covered topics}
   %\VignetteEngine{knitr::rmarkdown}
   %\VignetteEncoding{UTF-8}
 ---
@@ -34,9 +34,10 @@ read_all("../inst/records/") %>% repair() -> res
 ```
 We also used `repair` to fix a bunch of formatting issues in the records.
 
-For development purposes, we load the tables from csv files.
+For development purposes, we only fetch records if they are not already
+stored as csv files:
 ```{r}
-res <- read_from_csv('../inst/csv/')
+res <- read_from_csv_or_fetch('../inst/')
 ```
 
 ## Analysis

vignettes/genderequality.Rmd

@@ -1,8 +1,8 @@
 ---
-title: "genderequality"
+title: "Differences in gender"
 output: rmarkdown::html_vignette
 vignette: >
-  %\VignetteIndexEntry{genderequality}
+  %\VignetteIndexEntry{Differences in gender}
   %\VignetteEngine{knitr::rmarkdown}
   %\VignetteEncoding{UTF-8}
 ---
@@ -35,10 +35,13 @@ read_all("../records/") %>% repair() -> res
 ```
 We also used `repair` to fix a bunch of formatting issues in the records.
 
-For development purposes, we load the tables from csv files.
+For development purposes, we only fetch records if they are not already
+stored as csv files:
 ```{r}
-res <- read_from_csv('../inst/csv/')
+res <- read_from_csv_or_fetch('../inst/')
 ```
+
+
 and unpack our tibbles
 ```{r}
 comments <- res$comments

vignettes/generalquestions.Rmd

@@ -1,8 +1,8 @@
 ---
-title: "generalquestions"
+title: "General questions"
 output: rmarkdown::html_vignette
 vignette: >
-  %\VignetteIndexEntry{generalquestions}
+  %\VignetteIndexEntry{General questions}
   %\VignetteEngine{knitr::rmarkdown}
   %\VignetteEncoding{UTF-8}
 ---
@@ -34,9 +34,10 @@ read_all("../inst/records/") %>% repair() -> res
 ```
 We also used `repair` to fix a bunch of formatting issues in the records.
 
-For development purposes, we load the tables from csv files.
+For development purposes, we only fetch records if they are not already
+stored as csv files:
 ```{r}
-res <- read_from_csv('../inst/csv/')
+res <- read_from_csv_or_fetch('../inst/')
 ```
 
 ## Analysis

vignettes/hitlercomparison.Rmd

@@ -38,9 +38,10 @@ talks <- res$talks
 We also used `repair` to fix a bunch of formatting issues in the records and unpacked
 the result into more descriptive variables.
 
-For development purposes, we load the tables from csv files.
+For development purposes, we only fetch records if they are not already
+stored as csv files:
 ```{r}
-tables <- read_from_csv('../inst/csv/')
+tables <- read_from_csv_or_fetch('../inst/')
 
 comments <- tables$comments
 speeches <- tables$speeches

vignettes/interaction.Rmd

@@ -1,8 +1,8 @@
 ---
-title: "interaction"
+title: "Interaction between fractions"
 output: rmarkdown::html_vignette
 vignette: >
-  %\VignetteIndexEntry{interaction}
+  %\VignetteIndexEntry{Interaction between fractions}
   %\VignetteEngine{knitr::rmarkdown}
   %\VignetteEncoding{UTF-8}
 ---
@@ -34,9 +34,10 @@ read_all("../inst/records/") %>% repair() -> res
 ```
 We also used `repair` to fix a bunch of formatting issues in the records.
 
-For development purposes, we load the tables from csv files.
+For development purposes, we only fetch records if they are not already
+stored as csv files:
 ```{r}
-res <- read_from_csv('../inst/csv/')
+res <- read_from_csv_or_fetch('../inst/')
 ```
 
 ## Analysis