diff options
| -rw-r--r-- | Cargo.toml | 2 | ||||
| -rw-r--r-- | src/works/stories.rs | 23 |
2 files changed, 0 insertions, 25 deletions
@@ -11,5 +11,3 @@ serde = {version = "1.0", features = ["derive"]} serde_json = "1.0" anyhow = "1.0" chrono = {version = "0.4", features = ["serde"]} -pdf-extract = "0.6.4" -regex = "1.7.1" diff --git a/src/works/stories.rs b/src/works/stories.rs index 943f079..a38a7c0 100644 --- a/src/works/stories.rs +++ b/src/works/stories.rs @@ -71,29 +71,6 @@ impl Story { // extract text from pdf document fn get_text(&self) -> anyhow::Result<String> { - // TODO: - // - 1-2 digit number with linebreak e.g. "Es ist 10\n geworden" not usable in texts - // - currently only linebreaks before quotes, but not after paragraphs - /* - let mut text = - pdf_extract::extract_text(format!("docs/stories/{}", &self.path_to_document))?; - - text = regex::Regex::new(r"\n\n»")? - .replace_all(&text, "<br>»") - .to_string(); - text = regex::Regex::new(r"\d{1,2}?\n \d")? - .replace_all(&text, "") - .to_string(); - text = regex::Regex::new(r"-?\d{1,2}\n")? - .replace_all(&text, "") - .to_string(); - text = regex::Regex::new(r"-\n\n")? - .replace_all(&text, "") - .to_string(); - text = regex::Regex::new("\n\n")? - .replace_all(&text, " ") - .to_string(); - */ let text = std::fs::read_to_string(format!("stories_html/{}.html", self.path_to_document.replace(".pdf", "")))?; anyhow::Ok(text).with_context(|| format!("Failed to extract text for {}", self.title)) |