# ============================================================
# process_manifesto.R - Manifesto Project Data Processing
# ============================================================
# Processes Manifesto Project data for the two-dimensional party-position model
# Input: $PARTY2D_RAW_DATA_DIR/manifesto/MPDataset_MPDS2025a.csv
# Output: manifesto_data.csv
# ============================================================

library(tidyverse)
library(countrycode)
library(purrr)

# Set working directory (works both in RStudio and command line)
if (interactive() && requireNamespace("rstudioapi", quietly = TRUE)) {
  try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)), silent = TRUE)
}

cat("Processing Manifesto Project data...\n")

raw_data_dir <- Sys.getenv(
  "PARTY2D_RAW_DATA_DIR",
  unset = file.path("..", "..", "_local", "raw")
)
manifesto_raw_path <- file.path(raw_data_dir, "manifesto", "MPDataset_MPDS2025a.csv")
partyfacts_path <- file.path(raw_data_dir, "partyfacts", "partyfacts-external-parties.csv")

# ============================================================
# PartyFacts Linkage
# ============================================================

partyfacts_raw <- read_csv(partyfacts_path, show_col_types = FALSE)
manifesto_link <- partyfacts_raw %>%
  filter(dataset_key == "manifesto") %>%
  transmute(id = dataset_party_id,
            country = countrycode(country, origin = 'iso3c', destination = "iso2c"),
            party = partyfacts_id,
            party = ifelse(party == 622, 604, party))

# ============================================================
# Load Manifesto Data
# ============================================================

manifesto_data <- read_csv(manifesto_raw_path, show_col_types = FALSE)

# ============================================================
# CMP Code Mapping to 4 Dimensions
# ============================================================

vars <- tribble(
  ~type,          ~subtype,                 ~per_var,  ~stance,    ~label,
  # pro_market
  "pro_market",   "Market Regulation",      "per401",  "Positive", "Free Market Economy",
  "pro_market",   "Economic Liberalization","per402",  "Positive", "Incentives: Positive",
  "pro_market",   "Market Regulation",      "per407",  "Positive", "Protectionism: Negative",
  "pro_market",   "Economic Liberalization","per414",  "Positive", "Economic Orthodoxy",
  "pro_market",   "Economic Liberalization","per505",  "Positive", "Welfare State Limitation",
  "pro_market",   "Economic Liberalization","per507",  "Positive", "Education Limitation",
  "pro_market",   "Economic Liberalization","per702",  "Positive", "Labour Groups: Negative",
  "pro_market",   "Market Regulation",      "per406",  "Negative", "Protectionism: Positive",
  "pro_market",   "Market Regulation",      "per412",  "Negative", "Controlled Economy",
  "pro_market",   "Economic Liberalization","per504",  "Negative", "Welfare State Expansion",
  # pro_welfare
  "pro_welfare",  "Economic Intervention",  "per403",  "Positive", "Market Regulation",
  "pro_welfare",  "Economic Intervention",  "per404",  "Positive", "Economic Planning",
  "pro_welfare",  "Economic Intervention",  "per412",  "Positive", "Controlled Economy",
  "pro_welfare",  "Economic Intervention",  "per413",  "Positive", "Nationalisation",
  "pro_welfare",  "Social Services",        "per504",  "Positive", "Welfare State Expansion",
  "pro_welfare",  "Social Services",        "per506",  "Positive", "Education Expansion",
  "pro_welfare",  "Economic Intervention",  "per701",  "Positive", "Labour Groups: Positive",
  "pro_welfare",  "Economic Intervention",  "per401",  "Negative", "Free Market Economy",
  "pro_welfare",  "Social Services",        "per505",  "Negative", "Welfare State Limitation",
  # cosmopolitan
  "cosmopolitan", "Internationalism",       "per107",  "Positive", "Internationalism: Positive",
  "cosmopolitan", "Internationalism",       "per108",  "Positive", "European Community/Union: Positive",
  "cosmopolitan", "Multiculturalism",       "per607",  "Positive", "Multiculturalism: Positive",
  "cosmopolitan", "Multiculturalism",       "per201",  "Positive", "Freedom and Human Rights",
  "cosmopolitan", "Multiculturalism",       "per604",  "Positive", "traditional Morality: Negative",
  "cosmopolitan", "Internationalism",       "per109",  "Negative", "Internationalism: Negative",
  "cosmopolitan", "Multiculturalism",       "per601",  "Negative", "National Way of Life: Positive",
  # traditional
  "traditional",  "National Identity",      "per109",  "Positive", "Internationalism: Negative",
  "traditional",  "Conservative Morality",  "per110",  "Positive", "European Community/Union: Negative",
  "traditional",  "National Identity",      "per601",  "Positive", "National Way of Life: Positive",
  "traditional",  "Conservative Morality",  "per603",  "Positive", "traditional Morality: Positive",
  "traditional",  "Conservative Morality",  "per608",  "Positive", "Multiculturalism: Negative",
  "traditional",  "Conservative Morality",  "per605",  "Positive", "Law and Order: Positive",
  "traditional",  "National Identity",      "per107",  "Negative", "Internationalism: Positive",
  "traditional",  "Conservative Morality",  "per607",  "Negative", "Multiculturalism: Positive"
)

# ============================================================
# Process Manifesto Data
# ============================================================

manifesto <- vars %>%
  pmap_dfr(~ manifesto_data %>%
             transmute(country = countrycode(countryname, origin = 'country.name', destination = 'iso2c'),
                       year = as.numeric(format(as.Date(edate, format = "%d/%m/%Y"), "%Y")),
                       id = as.character(party),
                       count = round(.data[[..3]]),
                       var = ..3,
                       label = ..5,
                       type = ..1,
                       subtype = ..2,
                       stance = ..4,
                       project = 'Manifesto Project') %>%
             left_join(manifesto_link, by = c("id", "country")) %>%
             select(-id)) %>%
  group_by(party, country, year, subtype) %>%
  summarise(
    positive = sum(count[stance == "Positive"], na.rm = TRUE),
    sample = sum(count, na.rm = TRUE),
    type = first(type),
    project = first(project),
    .groups = "drop"
  ) %>%
  na.omit() %>%
  rename(var = subtype) %>%
  # Convert to bipolar bridge structure (type_high/type_low)
  mutate(
    type_high = case_when(
      type == "pro_welfare" ~ "pro_welfare",
      type == "pro_market" ~ "pro_market",
      type == "cosmopolitan" ~ "cosmopolitan",
      type == "traditional" ~ "traditional"
    ),
    type_low = case_when(
      type %in% c("pro_welfare", "pro_market") ~ ifelse(type == "pro_welfare", "pro_market", "pro_welfare"),
      type %in% c("cosmopolitan", "traditional") ~ ifelse(type == "cosmopolitan", "traditional", "cosmopolitan")
    )
  ) %>%
  select(-type) %>%
  # Add _manifesto suffix to variable names
  mutate(var = paste0(tolower(gsub(" ", "_", var)), "_manifesto"))

# ============================================================
# NOTE: Temporal continuity filter moved to the data setup orchestrator.
# This allows exempting parties that appear in parliamentary data
# (parties in parliament are by definition not fringe parties)
# ============================================================

cat("Skipping temporal filter (applied in 02_build_model_inputs.R after combining with other text data)\n")
cat(sprintf("  Parties: %d\n", n_distinct(manifesto$party)))

# ============================================================
# Write Output
# ============================================================

write_csv(manifesto, "manifesto_data.csv")
cat(sprintf("Output: manifesto_data.csv (%d rows, %d parties)\n",
            nrow(manifesto), n_distinct(manifesto$party)))

# ============================================================
# Election Data Extraction (vote shares)
# ============================================================

cat("\nExtracting election data (pervote)...\n")

election_data <- manifesto_data %>%
  transmute(
    country = countrycode(countryname, origin = 'country.name', destination = 'iso2c'),
    year = as.numeric(format(as.Date(edate, format = "%d/%m/%Y"), "%Y")),
    id = as.character(party),
    pervote = pervote
  ) %>%
  left_join(manifesto_link, by = c("id", "country")) %>%
  select(-id) %>%
  filter(!is.na(party), !is.na(pervote)) %>%
  # Keep one row per (party, country, year) — take max pervote if duplicates
  group_by(party, country, year) %>%
  summarise(pervote = max(pervote, na.rm = TRUE), .groups = "drop") %>%
  arrange(country, party, year)

write_csv(election_data, "election_data.csv")
cat(sprintf("Output: election_data.csv (%d rows, %d parties)\n",
            nrow(election_data), n_distinct(election_data$party)))

# Export manifesto_link for use by other scripts
# (poldem also needs it for CMP linkage)