raymon
/
wikipedia-infobox-analyzer
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Integrate property name lookup into the program output

Browse Source
Raymon Zutekouw 3 weeks ago
parent 4b8562089e
commit 8f61c26168
Signed by: raymon
GPG Key ID: 0E62222846283925
4 changed files with 79 additions and 57 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 2
      Cargo.lock
  2. 2
      Cargo.toml
  3. 68
      README.md
  4. 64
      src/main.rs

2
Cargo.lock generated
Unescape View File

@ -2386,7 +2386,7 @@ dependencies = [
[[package]]
name = "wikipedia-infobox-analyzer"
version = "0.1.0"
version = "0.2.0"
dependencies = [
"ascii_table",
"dirs-next",

2
Cargo.toml
Unescape View File

@ -1,6 +1,6 @@
[package]
name = "wikipedia-infobox-analyzer"
version = "0.1.0"
version = "0.2.0"
edition = "2021"
description = """
This analysis tool allows seeing the wikidata behind articles through the lens of the infoboxes.

68
README.md
Unescape View File

@ -38,46 +38,46 @@ If it is not present, the right column will be blank.
Remaining properties in wikidata that are not required by the infobox are trailed in the right column.
``` markdown
┌──────────────────┬─────────────────────┐
│ Infobox requires │ Wikidata Earth (Q2) │
├──────────────────┼─────────────────────┤
│ P18 │ P18 │ // property: image
│ P170 │ P170 │ // property: creator
│ P571 │ P571 │ // property: inception
│ │ P31 │ // property: instance of
│ │ P138 │ // property: inception
│ │ P361 │ // property: part of
│ │ .... │
└──────────────────┴─────────────────────┘
┌──────────────────┬─────────────────────┬───────────────┐
│ Infobox requires │ Wikidata Earth (Q2) │ Property name │
├──────────────────┼─────────────────────┼───────────────┤
│ P18 │ P18 │ image │
│ P170 │ P170 │ creator │
│ P571 │ P571 │ inception │
│ │ P31 │ │
│ │ P138 │ │
│ │ P361 │ │
│ │ .... │ │
└──────────────────┴─────────────────────┴───────────────┘
```
This (shortened) example is complete, but if we were to try a different infobox template on the earth entry you can see that it is not a good fit.
To demonstrate, we can apply the software template to the earth entry:
``` markdown
┌──────────────────┬─────────────────────┐
│ Infobox requires │ Wikidata Earth (Q2) │
├──────────────────┼─────────────────────┤
│ P18 │ P18 │ // property: image
│ P154 │ │
│ P170 │ P170 │ // property: creator
│ P178 │ │
│ P275 │ │
│ P277 │ │
│ P306 │ │
│ P348 │ │
│ P400 │ │
│ P548 │ │
│ P571 │ P571 │ // property: inception
│ P577 │ │
│ P856 │ │
│ P1324 │ │
│ P2096 │ │
│ │ P10 │
│ │ P31 │
│ │ P138 │
│ │ .... │
└──────────────────┴─────────────────────┘
┌──────────────────┬─────────────────────┬───────────────┐
│ Infobox requires │ Wikidata Earth (Q2) │ Property name │
├──────────────────┼─────────────────────┼───────────────┤
│ P18 │ P18 │ image │
│ P154 │ │ │
│ P170 │ P170 │ creator │
│ P178 │ │ │
│ P275 │ │ │
│ P277 │ │ │
│ P306 │ │ │
│ P348 │ │ │
│ P400 │ │ │
│ P548 │ │ │
│ P571 │ P571 │ inception │
│ P577 │ │ │
│ P856 │ │ │
│ P1324 │ │ │
│ P2096 │ │ │
│ │ P10 │ │
│ │ P31 │ │
│ │ P138 │ │
│ │ .... │ │
└──────────────────┴─────────────────────┴───────────────┘
```
## Templates

64
src/main.rs
Unescape View File

@ -88,6 +88,7 @@ impl Cache {
Ok(())
}
#[allow(dead_code)]
fn delete(&mut self) -> std::io::Result<()> {
fs::remove_file(self.storage.base_path.join(self.file_name.clone()))?;
self.property_labels = HashMap::new();
@ -96,17 +97,15 @@ impl Cache {
async fn lookup_property_name(&mut self, pid: u64) -> std::io::Result<String> {
let key = format!("P{pid}");
if self.property_labels.contains_key(&key) {
let name = self.property_labels.get(&key).unwrap().to_string();
return Ok(name);
if let Some(name) = self.property_labels.get(&key) {
return Ok(name.to_string());
}
// If the property name cannot be found, fetch the name
let name = fetch_name_for_wiki_property(pid).await;
// Update cache with new value, so it can be used the next time
self.property_labels
.insert(key, name.clone());
self.property_labels.insert(key, name.clone());
self.sync_to_storage()?;
Ok(name)
@ -114,7 +113,7 @@ impl Cache {
}
/// Creates an ascii table out of the properties
fn format_property_usage(name: String, qid: String, properties_template: Vec<u64>, properties_item: Vec<u64>, ) -> String {
fn format_property_usage(name: String, qid: String, properties_template: Vec<u64>, properties_item: Vec<u64>, properties_labels: Vec<String>) -> String {
let mut ascii_table = AsciiTable::default();
ascii_table.set_max_width(80);
ascii_table
@ -127,13 +126,25 @@ fn format_property_usage(name: String, qid: String, properties_template: Vec<u64
.set_header(format!("Wikidata {name} ({qid})"))
.set_align(Align::Left);
ascii_table
.column(2)
.set_header("Property name")
.set_align(Align::Left);
// Display the property columns as a table
let data: Vec<Vec<String>> = join_columns(&properties_template, &properties_item)
.iter()
.map(|&m| {
.enumerate()
.map(|(index, &m)| {
let (v1, v2) = m;
let property_name = if index >= properties_template.len() {
"".to_string()
} else {
properties_labels[index].clone()
};
vec![ v1.map_or("".to_owned(), |v| format!("P{v}").to_owned())
, v2.map_or("".to_owned(), |v| format!("P{v}").to_owned())]
, v2.map_or("".to_owned(), |v| format!("P{v}").to_owned())
, property_name]
}
).collect();
ascii_table.format(data)
@ -143,7 +154,7 @@ fn format_property_usage(name: String, qid: String, properties_template: Vec<u64
async fn main() -> Result<(), Box<dyn std::error::Error>> {
// Initialize cache and storage
let storage = StorageDisk::new("wikipedia-infobox-analyzer")?;
let mut _cache = Cache::new("property_labels.cache".to_string(), storage)?;
let mut cache = Cache::new("property_labels.cache".to_string(), storage)?;
// Input to the program
let args = Cli::from_args();
@ -153,13 +164,20 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
let qid = fetch_wiki_item_by_article_title(title.clone(), language.clone());
let properties_template = extract_used_properties_from_template(template);
let properties_item = fetch_properties_for_wiki_item(qid);
let mut properties_labels: Vec<String> = vec![];
for property in &properties_template {
let name = cache.lookup_property_name(*property).await?;
properties_labels.push(name);
}
let table = format_property_usage(
title.clone(),
format!("Q{qid}"),
properties_template,
properties_item,
properties_labels,
);
// Output of the program
@ -202,20 +220,24 @@ mod tests_main {
"Earth".to_string(),
"Q2".to_string(),
vec![18, 170, 571],
vec![18, 31, 138, 170, 361, 571]
vec![18, 31, 138, 170, 361, 571],
vec![ "image".to_string()
, "creator".to_string()
, "inception".to_string()
]
),
concat![
"┌──────────────────┬─────────────────────┐\n",
"│ Infobox requires │ Wikidata Earth (Q2) │\n",
"├──────────────────┼─────────────────────┤\n",
"│ P18 │ P18 │\n", // property: image
"│ P170 │ P170 │\n", // property: creator
"│ P571 │ P571 │\n", // property: inception
"│ │ P31 │\n", // property: instance of
"│ │ P138 │\n", // property: inception
"│ │ P361 │\n", // property: part of
"└──────────────────┴─────────────────────┘\n",
"┌──────────────────┬─────────────────────┬───────────────┐\n",
"│ Infobox requires │ Wikidata Earth (Q2) │ Property name │\n",
"├──────────────────┼─────────────────────┼───────────────┤\n",
"│ P18 │ P18 │ image │\n",
"│ P170 │ P170 │ creator │\n",
"│ P571 │ P571 │ inception │\n",
"│ │ P31 │ │\n",
"│ │ P138 │ │\n",
"│ │ P361 │ │\n",
"└──────────────────┴─────────────────────┴───────────────┘\n",
]
);
}

Write Preview
Loading…
Cancel
Save