File size: 7,990 Bytes
aa22659 8c8d1d0 aa22659 8c8d1d0 63efaec 9e029bd b287922 9e029bd b287922 9e029bd b287922 9e029bd 8c8d1d0 aa22659 743228e aa22659 743228e aa22659 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 | # scripts/export_seo_metadata.R
#
# Exports enriched DWD station metadata from all 5 resolution caches
# into a single JSON file for use by the Netlify Edge Function.
#
# Output: dwd-seo-metadata.json
#
# Usage:
# Rscript scripts/export_seo_metadata.R
# (run from the DWD app root directory)
# Ensure UTF-8 output
invisible(Sys.setlocale("LC_CTYPE", "en_US.UTF-8"))
library(jsonlite)
# ββ Slugification ββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
slugify <- function(text) {
s <- as.character(text)
# German umlaut / special char replacements (before NFD decomposition)
s <- gsub("\u00fc", "ue", s) # ΓΌ
s <- gsub("\u00f6", "oe", s) # ΓΆ
s <- gsub("\u00e4", "ae", s) # Γ€
s <- gsub("\u00dc", "Ue", s) # Γ
s <- gsub("\u00d6", "Oe", s) # Γ
s <- gsub("\u00c4", "Ae", s) # Γ
s <- gsub("\u00df", "ss", s) # Γ
# Lowercase
s <- tolower(s)
# Remove accents via iconv transliteration
s <- iconv(s, from = "UTF-8", to = "ASCII//TRANSLIT", sub = "")
# Replace non-alphanumeric with hyphens
s <- gsub("[^a-z0-9]+", "-", s)
# Trim leading/trailing hyphens
s <- gsub("^-+|-+$", "", s)
s
}
# ββ Resolution config ββββββββββββββββββββββββββββββββββββββββββββββββββββ
resolution_config <- list(
list(
key = "daily",
label = "Daily",
slug = "daily",
file = "www/tabs/dwd_stations_enriched_daily.rds"
),
list(
key = "hourly",
label = "Hourly",
slug = "hourly",
file = "www/tabs/dwd_stations_enriched.rds"
),
list(
key = "monthly",
label = "Monthly",
slug = "monthly",
file = "www/tabs/dwd_stations_enriched_monthly.rds"
),
list(
key = "annual",
label = "Annual",
slug = "annual",
file = "www/tabs/dwd_stations_enriched_annual.rds"
),
list(
key = "10_minutes",
label = "10 Minutes",
slug = "10-minutes",
file = "www/tabs/dwd_stations_enriched_10min.rds"
)
)
# ββ Main export ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
stations_out <- list()
states_out <- list()
resolutions_out <- list()
slug_map <- list()
for (rc in resolution_config) {
if (!file.exists(rc$file)) {
message("Skipping ", rc$key, ": file not found (", rc$file, ")")
next
}
df <- readRDS(rc$file)
message(rc$label, ": ", nrow(df), " stations loaded")
res_slug <- rc$slug
# ββ Per-state aggregation ββββββββββββββββββββββββββββββββββββββββββββ
state_counts <- list()
for (i in seq_len(nrow(df))) {
row <- df[i, ]
station_name <- enc2utf8(as.character(row$name))
station_id <- as.character(row$id)
state_name <- enc2utf8(as.character(row$state))
station_slug <- slugify(station_name)
state_slug <- slugify(state_name)
# Build path key: "daily/bayern/muenchen-flughafen"
path_key <- paste0(res_slug, "/", state_slug, "/", station_slug)
# Station entry
entry <- list(
id = station_id,
name = station_name,
state = state_name,
stateSlug = state_slug,
elevation = as.numeric(row$elevation),
lat = as.numeric(row$latitude),
lon = as.numeric(row$longitude),
resolution = rc$key,
resolutionLabel = rc$label,
resolutionSlug = res_slug,
overallStart = as.character(row$station_overall_start),
overallEnd = as.character(row$station_overall_end)
)
# Add detailed_summary if available
if ("detailed_summary" %in% names(row)) {
entry$availableParams <- as.character(row$detailed_summary)
}
stations_out[[path_key]] <- entry
# Track state counts
state_key <- paste0(res_slug, "/", state_slug)
if (is.null(state_counts[[state_key]])) {
state_counts[[state_key]] <- list(
state = state_name,
stateSlug = state_slug,
resolution = rc$key,
resolutionLabel = rc$label,
resolutionSlug = res_slug,
stationCount = 0L,
activeStationCount = 0L
)
}
state_counts[[state_key]]$stationCount <-
state_counts[[state_key]]$stationCount + 1L
# Determine the UI's default date range start for this resolution
# Must match server.R URL param handler for initial load
default_start_date <- switch(rc$key,
"10_minutes" = Sys.Date() - 30,
"hourly" = Sys.Date() - 366,
"monthly" = Sys.Date() - (365 * 6),
"daily" = Sys.Date() - (365 * 6),
"annual" = as.Date("1991-01-01"),
Sys.Date() - (365 * 6)
)
default_start_num <- as.numeric(format(default_start_date, "%Y%m%d"))
default_end_num <- as.numeric(format(Sys.Date(), "%Y%m%d"))
overall_start_str <- as.character(row$station_overall_start)
overall_end_str <- as.character(row$station_overall_end)
is_active <- FALSE
# Must match server.R filtered_stations():
# as.numeric(station_overall_start) <= range_end &
# as.numeric(station_overall_end) >= range_start
start_num <- suppressWarnings(as.numeric(overall_start_str))
end_num <- if (overall_end_str == "99999999") Inf else suppressWarnings(as.numeric(overall_end_str))
if (!is.na(start_num) && !is.na(end_num) &&
start_num <= default_end_num && end_num >= default_start_num) {
is_active <- TRUE
}
if (is_active) {
state_counts[[state_key]]$activeStationCount <-
state_counts[[state_key]]$activeStationCount + 1L
}
# Slug map (only need unique entries)
if (is.null(slug_map[[station_name]])) {
slug_map[[station_name]] <- station_slug
}
if (is.null(slug_map[[state_name]])) {
slug_map[[state_name]] <- state_slug
}
}
# Merge state entries
for (sk in names(state_counts)) {
states_out[[sk]] <- state_counts[[sk]]
}
# Resolution summary (including active count summed from states)
total_active <- sum(sapply(state_counts, function(sc) sc$activeStationCount))
resolutions_out[[res_slug]] <- list(
key = rc$key,
label = rc$label,
slug = res_slug,
stationCount = nrow(df),
activeStationCount = total_active
)
}
# ββ Assemble and write JSON ββββββββββββββββββββββββββββββββββββββββββββββ
output <- list(
stations = stations_out,
states = states_out,
resolutions = resolutions_out,
slugMap = slug_map
)
output_path <- "dwd-seo-metadata.json"
json_str <- toJSON(output, pretty = TRUE, auto_unbox = TRUE)
writeLines(json_str, output_path)
message("\nExported ", length(stations_out), " station entries, ",
length(states_out), " state entries, ",
length(resolutions_out), " resolutions")
message("Output: ", normalizePath(output_path))
|