Original Text

# read the epub
book_text <- epubr::epub("Do Nothing - Celeste Headlee.epub")
book_text$data[[1]] %>% 
  mutate(text = str_sub(text, 0, 20),
         text = paste(text, "...")) %>% 
  gt::gt() # needs to get the text stings truncated

# A simple slice operation would do
book_txt <- book_text$data[[1]] %>% 
  slice(6:24)

# bind previous word and character counts
<- book_txt %>% 
  select(section, nword, nchar) %>% 
  mutate(part = paste0("part", 5:23)) %>% 
  select(-section)

# extract the text
match_df <- stringr::str_locate_all(book_txt$text, '"(.*?)"') %>% 
  # give names for future binding
  # parts go from 5 to 23 (idx goes 6:24)
  set_names(nm = paste0("part", 5:23)) %>% 
  # convert into tibble for easy binding
  map(as_tibble) %>% 
  bind_rows(.id =  "part")

# This is an example
match_df %>% 
  slice(8:10) %>% 
  mutate(quote = map2_chr(
    start, end,  
    function(.x, .y) str_sub(book_txt$text[[1]], .x, .y)
  )) %>% 
  gt::gt() %>%
  gt::tab_style(
    style = gt::cell_text(weight = "bold"),
    locations = gt::cells_column_labels()
        )

threshold <- 100  # Define your threshold

merged_quotes <- match_df %>%
  mutate(
    .by = part, 
    prev_end = lag(end),
    distance = start - prev_end,
    merge_group = cumsum(ifelse(is.na(distance) | distance > threshold, 1, 0))
  ) 

# 
head(merged_quotes, n = 10)

# A tibble: 10 × 6
   part  start   end prev_end distance merge_group
   <chr> <int> <int>    <int>    <int>       <dbl>
 1 part5   574   597       NA       NA           1
 2 part5  1342  1361      597      745           2
 3 part5  1876  1904     1361      515           3
 4 part5  6036  6051     1904     4132           4
 5 part5  8751  8944     6051     2700           5
 6 part5  9276  9373     8944      332           6
 7 part5 13258 13265     9373     3885           7
 8 part5 14893 14905    13265     1628           8
 9 part5 16002 16132    14905     1097           9
10 part5 16186 16336    16132       54           9

merged_quotes <- merged_quotes %>%
  summarize(
    .by = c(merge_group, part),
    part = first(part),
    start = first(start),
    end = last(end)
  ) %>% 
  # add the lag again to see where the original text starts
  mutate(text_start = lag(end, default = 0), .by = part)

# pad parts  for plotting
format_part <- function(part_name) {
  # Extract the numeric part
  part_number <- as.integer(str_extract(part_name, "\\d+"))

  # Pad the number with zeros and prepend 'part'
  formatted_part <- str_c("part", str_pad(part_number, width = 2, pad = "0"))
  
  return(formatted_part)
}

# make tail end segments
tail_data <- merged_quotes %>% 
  summarise(.by = part, last_quote_end = max(end)) %>% 
  left_join(meta, by='part') %>% 
  # fix the padding after merging
  mutate(part = format_part(part))

# fix the padding here too
merged_quotes <- merged_quotes  %>% mutate(part = format_part(part))


ggplot(data=merged_quotes) + 
  geom_ethogram(aes(x=text_start, xend=start, y = part), color ="gray30") +
  geom_ethogram(data=tail_data, aes(x=last_quote_end, 
                                    xend=nchar, y = part), color ="gray30") +
  geom_ethogram(aes(x=start, xend=end, y = part), color = "red")+
  cowplot::theme_nothing() +
  labs(title = "'Do Nothing' is Peppered by Quotes",
       subtitle = "<span style = 'color:gray30'>Original Text</span> and <span style = 'color:red'>Verbatim quotes</span>",
       caption = "Viz: Matias Andina",
       y = "Chapter") +
  theme(
    plot.title = element_text(hjust = 0.5),
    plot.subtitle = ggtext::element_markdown(hjust = 0.5),
    plot.background = element_rect(fill = "black"),
    text = element_text(color = 'gray80'),
    axis.title.y = element_text(angle = 90),
    plot.caption = element_text(size = 8, hjust = .95))

match_df %>% 
  mutate(quote_chars = end - start) %>% 
  summarise(.by = part, 
            quote_chars = sum(quote_chars)) %>% 
  left_join(meta, by = "part") %>% 
  mutate(quote_frac = quote_chars / nchar,
         part = fct_reorder(part, quote_frac)) %>% 
  ggplot() +
  geom_hline(aes(yintercept = mean(quote_frac)), lty = 4) +
  geom_point(aes(as.numeric(part), quote_frac), 
             size = 4, alpha = 0.9, color = "darkred") +
  geom_label(aes(x = 15.5, y = 0.17,
                 label = paste(part[which.max(quote_frac)],
                               scales::percent(max(quote_frac)),
                               sep="\n"
                 ))) +
  scale_y_continuous(labels = scales::label_percent(),
                     expand = expansion(add = c(0.01, 0.05)))+
  labs(y = "Verbatim Quotes",
       x = "Book Part\n(ascending quote % order)",
       title = "'Do Nothing' contains ~10% verbatim quoted text",
       subtitle = "Some parts are as high as 17%!")+
  cowplot::theme_minimal_hgrid()

Footnotes

1. But I’m sure a copyright lawyer would know much more than I do regarding how much verbatim text you can include and still claim ownership of your work.↩︎

2. Of course, this threshold is arbitrary. How did I come up with it? I asked ChatGPT to come up with 10 interjections that were a bit longer than “they said” and phrases where sitting comfortably around 50. I doubled it to be super sure that we were not missing instances.↩︎

3. This paragraph was indeed a paraphrase of my editor’s (read wife’s) reaction to my article. Talking to her is a great exercise in positive reframing.↩︎

Reuse

Citation

@online{andina2023,
  author = {Andina, Matias},
  title = {Original {Text}},
  date = {2023-11-07},
  url = {https://matiasandina.com/posts/2023-11-07-original-text},
  langid = {en}
}