xenofem/poop-graph
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases Wiki Activity

updates for everyone

Browse source
This commit is contained in:
xenofem 2025-09-25 00:45:33 -04:00
parent fda5f2bbba
commit 2c7484b538
4 changed files with 1283 additions and 895 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/extract.rs
View file

@ -1,7 +1,7 @@
use std::{collections::HashMap, sync::Arc};
use lazy_static::lazy_static;
use pdf::{backend::Backend, content::{Op, Point, TextDrawAdjusted}};
use pdf::{backend::Backend, content::{Op, Point, TextDrawAdjusted}, file::{NoCache, NoLog}};
use regex::Regex;
use time::Date;
@ -28,7 +28,7 @@ pub enum Error {
}
impl DataSet {
pub fn extract<B: Backend>(doc: &pdf::file::File<B>) -> Result<Self, Error> {
pub fn extract<B: Backend>(doc: &pdf::file::File<B, NoCache, NoCache, NoLog>) -> Result<Self, Error> {
let mut doc_iter = DocumentIterator::new(doc).peekable();
let mut columns: Vec<(Arc<String>, f32)> = Vec::new();
@ -113,13 +113,13 @@ struct DocumentIterator<'a> {
}
impl<'a> DocumentIterator<'a> {
fn new<B: Backend>(document: &'a pdf::file::File<B>) -> Self {
fn new<B: Backend>(document: &'a pdf::file::File<B, NoCache, NoCache, NoLog>) -> Self {
Self {
point: Point { x: 0.0, y: 0.0 },
operations: Box::new(
document
.pages()
.filter_map(|page| Some(page.ok()?.contents.clone()?.operations(document).ok()?.into_iter()))
.filter_map(|page| Some(page.ok()?.contents.clone()?.operations(&document.resolver()).ok()?.into_iter()))
.flatten(),
),
}

9
src/fetch.rs
View file

@ -6,6 +6,7 @@ use std::{
use futures::{sink::SinkExt, TryStreamExt};
use lazy_static::lazy_static;
use log::{info, warn};
use pdf::file::{NoCache, NoLog};
use reqwest::Url;
use scraper::Selector;
use time::PrimitiveDateTime;
@ -13,7 +14,7 @@ use tokio_util::codec;
lazy_static! {
static ref CHARTS_URL: Url = Url::parse("https://www.mwra.com/biobot/biobotdata.htm").unwrap();
static ref PDF_SEL: Selector = Selector::parse(r#"a[href^="/media/file/mwradata"][href$="-data"]"#).unwrap();
static ref PDF_SEL: Selector = Selector::parse(r#"a[href^="/media/file/mwradata"][href$="-datapdf"]"#).unwrap();
static ref MIN_CHECK_INTERVAL: Duration = Duration::from_secs(300);
}
@ -54,7 +55,7 @@ impl PdfFetcher {
})
}
pub async fn fetch(&mut self) -> Result<pdf::file::File<Vec<u8>>, Error> {
pub async fn fetch(&mut self) -> Result<pdf::file::File<Vec<u8>, NoCache, NoCache, NoLog>, Error> {
info!("Fetching data PDF");
let cache_modtime = match tokio::fs::File::open(&self.cached_pdf_path).await {
@ -145,7 +146,7 @@ impl PdfFetcher {
self.cached_pdf()
}
fn cached_pdf(&self) -> Result<pdf::file::File<Vec<u8>>, Error> {
Ok(pdf::file::File::open(&self.cached_pdf_path)?)
fn cached_pdf(&self) -> Result<pdf::file::File<Vec<u8>, NoCache, NoCache, NoLog>, Error> {
Ok(pdf::file::FileOptions::uncached().open(&self.cached_pdf_path)?)
}
}