Peterbe.com

tl;dr; To make 2 lists into 1 without mutating them use list1 + list2.

I'm blogging about this because today I accidentally complicated my own code. From now on, let's just focus on the right way.

Suppose you have something like this:

winners = [123, 503, 1001]
losers = [45, 812, 332]

combined = winners + losers

that will create a brand new list. To prove that it's immutable:

>>> combined.insert(0, 100)
>>> combined
[100, 123, 503, 1001, 45, 812, 332]
>>> winners
[123, 503, 1001]
>>> losers
[45, 812, 332]

What I originally did was:

winners = [123, 503, 1001]
losers = [45, 812, 332]

combined = [*winners, *losers]

This works the same and that syntax feels very JavaScript'y. E.g.

> var winners = [123, 503, 1001]
[ 123, 503, 1001 ]
> var losers = [45, 812, 332]
[ 45, 812, 332 ]
> var combined = [...winners, ...losers]
[ 123, 503, 1001, 45, 812, 332 ]
> combined.pop()
332
> losers
[ 45, 812, 332 ]

By the way, if you want to filter out duplicates, do this:

>>> a = [1, 2, 3]
>>> b = [2, 3, 4]
>>> list(dict.fromkeys(a + b))
[1, 2, 3, 4]

It's the most performant way to do it if the order is important.

And if you don't care about the order you can use this:

>>> a = [1, 2, 3]
>>> b = [2, 3, 4]
>>> list(set(a + b))
[1, 2, 3, 4]
>>> list(set(b + a))
[1, 2, 3, 4]

This is how MDN Web Docs uses Elasticsearch. Daily, we build all the content and then upload it all using elasticsearch-dsl using aliases. Because there are no good complete guides to do this, I thought I'd write it down for the next person who needs to do something similar. Let's jump straight into the code. The reader will need a healthy dose of imagination to fill in their details.

Indexing

# models.py

from datetime.datetime import utcnow

from elasticsearch_dsl import Document

PREFIX = "myprefix"


class MyDocument(Document):
    title = Text()
    body = Text()
    # ...

    class Index:
        name = (
            f'{PREFIX}_{utcnow().strftime("%Y%m%d%H%M%S")}'
        )

What's important to note here is that the MyDocument.Index.name is dynamically allocated every single time the module is imported. It's not very important exactly what it is called but it's important that it becomes unique each time.
This means that when you start using MyDocument it will automatically figure out which index to use. Now, it's time to create the index and bulk publish it.

# index.py
# Note! This example code skips over things like progress bars
# and verbose logging and misc sanity checks and stuff.

from elasticsearch.helpers import parallel_bulk
from elasticsearch_dsl import Index
from elasticsearch_dsl.connections import connections

from .models import MyDocument, PREFIX


def index(buildroot: Path, url: str, update=False):
    """
    * 'buildroot' is where the files are we're going to read and index
    * 'url' is the host URL for the Elasticsearch server
    * 'update' is if just want to "cake on" a couple of documents 
      instead of starting over and doing a complete indexing.
    """

    # Connect and stuff
    connections.create_connection(hosts=[url], retry_on_timeout=True)
    connection = connections.get_connection()
    health = connection.cluster.health()
    status = health["status"]
    if status not in ("green", "yellow"):
        raise Exception(f"status {status} not green or yellow")

    if update:
        for name in connection.indices.get_alias():
            if name.startswith(f"{PREFIX}_"):
                document_index = Index(name)
                break
        else:
            raise IndexAliasError(
                f"Unable to find an index called {PREFIX}_*"
            )

    else:
        # Confusingly, `._index` is actually not a private API.
        # It's the documented way you're supposed to reach it.
        document_index = MyDocument._index
        document_index.create()

    def generator():
        for doc in Path(buildroot):
            # The reason for specifying the exact index name is that we might
            # be doing an update and if you don't specify it, elasticsearch_dsl
            # will fall back to using whatever Document._meta.Index automatically
            # becomes in this moment.
            yield to_search(doc, _index=document_index._name).to_dict(True)

    for success, info in parallel_bulk(connection, generator()):
        # 'success' is a boolean
        # 'info' has stuff like:
        #  - info["index"]["error"]
        #  - info["index"]["_shards"]["successful"]
        #  - info["index"]["_shards"]["failed"]
        pass

    if update:
        # When you do an update, Elasticsearch will internally delete the
        # previous docs (based on the _id primary key we set).
        # Normally, Elasticsearch will do this when you restart the cluster
        # but that's not something we usually do.
        # See https://www.elastic.co/guide/en/elasticsearch/reference/current/indices-forcemerge.html
        document_index.forcemerge()
    else:
        # Now we're going to bundle the change to set the alias to point
        # to the new index and delete all old indexes.
        # The reason for doing this together in one update is to make it atomic.
        alias_updates = [
            {"add": {"index": document_index._name, "alias": PREFIX}}
        ]
        for index_name in connection.indices.get_alias():
            if index_name.startswith(f"{PREFIX}_"):
                if index_name != document_index._name:
                    alias_updates.append({"remove_index": {"index": index_name}})
        connection.indices.update_aliases({"actions": alias_updates})

    print("All done!")



def to_search(file: Path, _index=None):
    with open(file) as f:
        data = json.load(f)
    return MyDocument(
        _index=_index,
        _id=data["identifier"],
        title=data["title"],
        body=data["body"]
    )

A lot is left to the reader as an exercise to fill in but these are the most important operations. It demonstrates how you can

1. Correctly create indexes
2. Atomically create an alias and clean up old indexes (and aliases)
3. How you can add to an existing index

After you've run this you'll see something like this:

$ curl http://localhost:9200/_cat/indices?v
...
health status index                   uuid                   pri rep docs.count docs.deleted store.size pri.store.size
yellow open   myprefix_20210514141421 vulVt5EKRW2MNV47j403Mw   1   1      11629            0     28.7mb         28.7mb

$ curl http://localhost:9200/_cat/aliases?v
...
alias    index                   filter routing.index routing.search is_write_index
myprefix myprefix_20210514141421 -      -             -              -

Searching

When it comes to using the index, well, it depends on where your code for that is. For example, on MDN Web Docs, the code that searches the index is in an entirely different code-base. It's incidentally Python (and elasticsearch-dsl) in both places but other than that they have nothing in common. So for the searching, you need to manually make sure you write down the name of the index (or name of the alias if you prefer) into the code that searches. For example:

from elasticsearch_dsl import Search

def search(params):
    search_query = Search(index=settings.SEARCH_INDEX_NAME)

    # Do stuff to 'search_query' based on 'params'

    response = search_query.execute()   
    for hit in response:
        # ...

If you're within the same code that has that models.MyDocument in the first example code above, you can simply do things like this:

from elasticsearch_dsl import Index
from elasticsearch_dsl.connections import connections

from .models import PREFIX


def analyze(
    url: str,
    text: str,
    analyzer: str,
):
    connections.create_connection(hosts=[url])
    index = Index(PREFIX)
    analysis = index.analyze(body={"text": text, "analyzer": analyzer})
    # ...

The list of stop words in Elasticsearch is:

a, an, and, are, as, at, be, but, by, for, if, in, into, 
is, it, no, not, of, on, or, such, that, the, their, 
then, there, these, they, this, to, was, will, with

The list of JavaScript reserved keywords is:

abstract, arguments, await, boolean, break, byte, case, 
catch, char, class, const, continue, debugger, default, 
delete, do, double, else, enum, eval, export, extends, 
false, final, finally, float, for, function, goto, if, 
implements, import, in, instanceof, int, interface, let, 
long, native, new, null, package, private, protected, 
public, return, short, static, super, switch, synchronized, 
this, throw, throws, transient, true, try, typeof, var, 
void, volatile, while, with, yield

That means that the overlap is:

for, if, in, this, with

And the remainder of the English stop words is:

a, an, and, are, as, at, be, but, by, into, is, it, no, 
not, of, on, or, such, that, the, their, then, there, 
these, they, to, was, will

Why does this matter? It matters when you're writing a search engine on English text that is about JavaScript. Such as, MDN Web Docs. At the time of writing, you can search for this because there's a special case explicitly for that word. But you can't search for for which is unfortunate.

But there's more! I think we should consider certain prototype words to be considered "reserved" because they are important JavaScript words that should not be treated as stop words. For example...

• of - from for (const thing of things) or Array.of(...)
• String.prototype.at
• Object.is()

Suppose you have one of those React apps that lazy-load some chunk. It just basically means it injects a .js static asset URL into the DOM and once it's downloaded by the browser, it carries on the React rendering with the new code loaded. Well, what if the network is really slow? In local development, it can be hard to simulate this. You can mess with the browser's Devtools to try to slow down the network, but even that can be too fast sometimes.

What I often do is, I take this:

const SettingsApp = React.lazy(() => import("./app"));

...and change it to this:

const SettingsApp = React.lazy(() =>
  import("./app").then((module) => {
    return new Promise((resolve) => {
      setTimeout(() => {
        resolve(module as any);
      }, 10000);
    });
  })
);

Now, it won't load that JS chunk until 10 seconds later. Only temporarily, in local development.

I know it's admittedly just a hack but it's nifty. Just don't forget to undo it when you're done simulating your snail-speed web app.

PS. That resolve(module as any); is for TypeScript. You can just change that to resolve(module); if it's regular JavaScript.

I edit a file called files/en-us/glossary/bézier_curve/index.html and then type git status and I get this:

▶ git status
...
Changes not staged for commit:
  ...
    modified:   "files/en-us/glossary/b\303\251zier_curve/index.html"

...

What's that?! First of all, I actually had this wrapped in a Python script that uses GitPython to analyze the output of for change in repo.index.diff(None):. So I got...

FileNotFoundError: [Errno 2] No such file or directory: '"files/en-us/glossary/b\\303\\251zier_curve/index.html"'

What's that?!

At first, I thought it was something wrong with how I use GitPython and thought I could force some sort of conversion to UTF-8 with Python. That, and to strip the quotation parts with something like path = path[1:-1] if path.startwith('"') else path

After much googling and experimentation, what totally solved all my problems was to run:

▶ git config --global core.quotePath false

Now you get...:

▶ git status
...
Changes not staged for commit:
  ...
    modified:   files/en-us/glossary/bézier_curve/index.html

...

And that also means it works perfectly fine with any GitPython code that does something with the repo.index.diff(None) or repo.index.diff(repo.head.commit).

Also, we I use the git-diff-action GitHub Action which would fail to spot files that contained umlauts but now I run this:

    steps:
       - uses: actions/checkout@v2
+
+      - name: Config git core.quotePath
+        run: git config --global core.quotePath false
+
       - uses: technote-space/get-diff-action@v4.0.6
         id: git_diff_content
         with:

Sorry about the weird title of this blog post. Not sure what else to call it.

I have a function that recursively traverses the file system. You can iterate over this function to do something with each found file on disk. Silly example:

for (const filePath of walker("/lots/of/files/here")) {
  count += filePath.length;
}

The implementation looks like this:

function* walker(root) {
  const files = fs.readdirSync(root);
  for (const name of files) {
    const filepath = path.join(root, name);
    const isDirectory = fs.statSync(filepath).isDirectory();
    if (isDirectory) {
      yield* walker(filepath);
    } else {
      yield filepath;
    }
  }
}

But I wondered; is it faster to not use a generator function since there might an overhead in swapping from the generator to whatever callback does something with each yielded thing. A pure big-array function looks like this:

function walker(root) {
  const files = fs.readdirSync(root);
  const all = [];
  for (const name of files) {
    const filepath = path.join(root, name);
    const isDirectory = fs.statSync(filepath).isDirectory();
    if (isDirectory) {
      all.push(...walker(filepath));
    } else {
      all.push(filepath);
    }
  }
  return all;
}

It gets the same result/outcome.

It's hard to measure this but I pointed it to some large directory with many files and did something silly with each one just to make sure it does something:

const label = "generator";
console.time(label);
let count = 0;
for (const filePath of walker(SEARCH_ROOT)) {
  count += filePath.length;
}
console.timeEnd(label);
const heapBytes = process.memoryUsage().heapUsed;
console.log(`HEAP: ${(heapBytes / 1024.0).toFixed(1)}KB`);

I ran it a bunch of times. After a while, the numbers settle and you get:

• Generator function: (median time) 1.74s
• Big array function: (median time) 1.73s

In other words, no speed difference.

Obviously building up a massive array in memory will increase the heap memory usage. Taking a snapshot at the end of the run and printing it each time, you can see that...

• Generator function: (median heap memory) 4.9MB
• Big array function: (median heap memory) 13.9MB

Conclusion

The potential swap overhead for a Node generator function is absolutely minuscule. At least in contexts similar to mine.

It's not unexpected that the generator function bounds less heap memory because it doesn't build up a big array at all.

tl;dr; Periodically, the whole of MDN is built, by our Node code, in a GitHub Action. A Python script bulk-publishes this to Elasticsearch. Our Django server queries the same Elasticsearch via /api/v1/search. The site-search page is a static single-page app that sends XHR requests to the /api/v1/search endpoint. Search results' sort-order is determined by match and "popularity".

Jamstack'ing

The challenge with "Jamstack" websites is with data that is too vast and dynamic that it doesn't make sense to build statically. Search is one of those. For the record, as of Feb 2021, MDN consists of 11,619 documents (aka. articles) in English. Roughly another 40,000 translated documents. In English alone, there are 5.3 million words. So to build a good search experience we need to, as a static site build side-effect, index all of this in a full-text search database. And Elasticsearch is one such database and it's good. In particular, Elasticsearch is something MDN is already quite familiar with because it's what was used from within the Django app when MDN was a wiki.

Note: MDN gets about 20k site-searches per day from within the site.

Build

When we build the whole site, it's a script that basically loops over all the raw content, applies macros and fixes, dumps one index.html (via React server-side rendering) and one index.json. The index.json contains all the fully rendered text (as HTML!) in blocks of "prose". It looks something like this:

{
  "doc": {
    "title": "DOCUMENT TITLE",
    "summary": "DOCUMENT SUMMARY",
    "body": [
      {
        "type": "prose", 
        "value": {
          "id": "introduction", 
          "title": "INTRODUCTION",
          "content": "<p>FIRST BLOCK OF TEXTS</p>"
       }
     },
     ...
   ],
   "popularity": 0.12345,
   ...
}

You can see one here: /en-US/docs/Web/index.json

Indexing

Next, after all the index.json files have been produced, a Python script takes over and it traverses all the index.json files and based on that structure it figures out the, title, summary, and the whole body (as HTML).

Next up, before sending this into the bulk-publisher in Elasticsearch it strips the HTML. It's a bit more than just turning <p>Some <em>cool</em> text.</p> to Some cool text. because it also cleans up things like <div class="hidden"> and certain <div class="notecard warning"> blocks.

One thing worth noting is that this whole thing runs roughly every 24 hours and then it builds everything. But what if, between two runs, a certain page has been removed (or moved), how do you remove what was previously added to Elasticsearch? The solution is simple: it deletes and re-creates the index from scratch every day. The whole bulk-publish takes a while so right after the index has been deleted, the searches won't be that great. Someone could be unlucky in that they're searching MDN a couple of seconds after the index was deleted and now waiting for it to build up again.
It's an unfortunate reality but it's a risk worth taking for the sake of simplicity. Also, most people are searching for things in English and specifically the Web/ tree so the bulk-publishing is done in a way the most popular content is bulk-published first and the rest was done after. Here's what the build output logs:

Found 50,461 (potential) documents to index
Deleting any possible existing index and creating a new one called mdn_docs
Took 3m 35s to index 50,362 documents. Approximately 234.1 docs/second
Counts per priority prefixes:
    en-us/docs/web                 9,056
    *rest*                         41,306

So, yes, for 3m 35s there's stuff missing from the index and some unlucky few will get fewer search results than they should. But we can optimize this in the future.

Searching

The way you connect to Elasticsearch is simply by a URL it looks something like this:

https://USER:PASSWD@HASH.us-west-2.aws.found.io:9243

It's an Elasticsearch cluster managed by Elastic running inside AWS. Our job is to make sure that we put the exact same URL in our GitHub Action ("the writer") as we put it into our Django server ("the reader").
In fact, we have 3 Elastic clusters: Prod, Stage, Dev.
And we have 2 Django servers: Prod, Stage.
So we just need to carefully make sure the secrets are set correctly to match the right environment.

Now, in the Django server, we just need to convert a request like GET /api/v1/search?q=foo&locale=fr (for example) to a query to send to Elasticsearch. We have a simple Django view function that validates the query string parameters, does some rate-limiting, creates a query (using elasticsearch-dsl) and packages the Elasticsearch results back to JSON.

How we make that query is important. In here lies the most important feature of the search; how it sorts results.

In one simple explanation, the sort order is a combination of popularity and "matchness". The assumption is that most people want the popular content. I.e. they search for foreach and mean to go to /en-US/docs/Web/JavaScript/Reference/Global_Objects/Array/forEach not /en-US/docs/Web/API/NodeList/forEach both of which contains forEach in the title. The "popularity" is based on Google Analytics pageviews which we download periodically, normalize into a floating-point number between 1 and 0. At the of writing the scoring function does something like this:

rank = doc.popularity * 10 + search.score

This seems to produce pretty reasonable results.

But there's more to the "matchness" too. Elasticsearch has its own API for defining boosting and the way we apply is:

• match phrase in the title: Boost = 10.0
• match phrase in the body: Boost = 5.0
• match in title: Boost = 2.0
• match in body: Boost = 1.0

This is then applied on top of whatever else Elasticsearch does such as "Term Frequency" and "Inverse Document Frequency" (tf and if). This article is a helpful introduction.

We're most likely not done with this. There's probably a lot more we can do to tune this myriad of knobs and sliders to get the best possible ranking of documents that match.

Web UI

The last piece of the puzzle is how we display all of this to the user. The way it works is that developer.mozilla.org/$locale/search returns a static page that is blank. As soon as the page has loaded, it lazy-loads JavaScript that can actually issue the XHR request to get and display search results. The code looks something like this:

function SearchResults() {
  const [searchParams] = useSearchParams();
  const sp = createSearchParams(searchParams);
  // add defaults and stuff here
  const fetchURL = `/api/v1/search?${sp.toString()}`;

  const { data, error } = useSWR(
    fetchURL,
    async (url) => {
      const response = await fetch(URL);
      // various checks on the response.statusCode here
      return await response.json();
    }
  );

  // render 'data' or 'error' accordingly here

A lot of interesting details are omitted from this code snippet. You have to check it out for yourself to get a more up-to-date insight into how it actually works. But basically, the window.location (and pushState) query string drives the fetch() call and then all the component has to do is display the search results with some highlighting.

The /api/v1/search endpoint also runs a suggestion query as part of the main search query. This extracts out interest alternative search queries. These are filtered and scored and we issue "sub-queries" just to get a count for each. Now we can do one of those "Did you mean...". For example: search for intersections.

In conclusion

There are a lot of interesting, important, and careful details that are glossed over here in this blog post. It's a constantly evolving system and we're constantly trying to improve and perfect the system in a way that it fits what users expect.

A lot of people reach MDN via a Google search (e.g. mdn array foreach) but despite that, nearly 5% of all traffic on MDN is the site-search functionality. The /$locale/search?... endpoint is the most frequently viewed page of all of MDN. And having a good search engine that's reliable is nevertheless important. By owning and controlling the whole pipeline allows us to do specific things that are unique to MDN that other websites don't need. For example, we index a lot of raw HTML (e.g. <video>) and we have code snippets that needs to be searchable.

Hopefully, the MDN site-search will elevate from being known to be very limited to something now that can genuinely help people get to the exact page better than Google can. Yes, it's worth aiming high!

tl;dr; polka is the lightest Node HTTP server package.

Highly unscientific but nevertheless worth writing down. Lightest here refers to the eventual weight added to the node_modules directory which is a reflection of network and disk use.

When you write a serious web server in Node you probably don't care about which one is lightest. It's probably more important which ones are actively maintained, reliable, well documented, and generally "more familiar". However, I was interested in setting up a little Node HTTP server for the benefit of wrapping some HTTP endpoints for an integration test suite.

The test

In a fresh new directory, right after having run: yarn init -y run the yarn add ... and see how big the node_modules directory becomes afterward (du -sh node_modules).

The results

1. polka: 116K
2. koa: 1.7M
3. express: 2.4M
4. fastify: 8.0M

Conclusion

polka is the lightest. But I'm not so sure it matters. But it could if this has to be installed a lot. For example, in CI where you run that yarn install a lot. Then it might save quite a bit of electricity for the planet.

There are a lot of 'rss' related NPM packages but I think I've found a combination that is great for parsing RSS feeds. Something that takes up the minimal node_modules and works great. I think the killer combination is

• got for downloading, and,
• fast-xml-parser for parsing them

The code impressively simple:

const got = require("got");
const parser = require("fast-xml-parser");

(async function main() {
  const buffer = await got("https://hacks.mozilla.org/feed/", {
    responseType: "buffer",
    resolveBodyOnly: true,
    timeout: 5000,
    retry: 5,
  });
  var feed = parser.parse(buffer.toString());
  for (const item of feed.rss.channel.item) {
    console.log({ title: item.title, url: item.link });
    break;
  }
})();


// Outputs...
// {
//   title: 'MDN localization update, February 2021',
//   url: 'https://hacks.mozilla.org/2021/02/mdn-localization-update-february-2021/'
// }

I like about fast-xml-parser is that it has no dependencies. And it's tiny:

▶ du -sh node_modules/fast-xml-parser
104K    node_modules/fast-xml-parser

The got package is quite a bit larger and has more dependencies. But I still love it. It's proven itself to be very reliable and very pleasant API. Both packages support TypeScript too.

A particular detail I like about fast-xml-parser is that it doesn't try to do the downloading part too. This way, I can use my own preferred library and I could potentially write my own caching code if I want to protect against flaky network.

What do you think this code will print out?

function validateURL(url) {
  if (url.includes("://")) {
    const url = new URL(url);
    return url.protocol === "https:";
  } else {
    return "dunno";
  }
}
console.log(validateURL("http://www.peterbe.com"));

I'll give you a clue that isn't helpful,

▶ eslint --version
v7.19.0

▶ eslint code.js

▶ echo $?
0

OK, the answer is that it crashes:

▶ node code.js
/Users/peterbe/dev/JAVASCRIPT/catching_consts/code.js:3
    const url = new URL(url);
                        ^

ReferenceError: Cannot access 'url' before initialization
    at validateURL (/Users/peterbe/dev/JAVASCRIPT/catching_consts/code.js:3:25)
    at Object.<anonymous> (/Users/peterbe/dev/JAVASCRIPT/catching_consts/code.js:9:13)
...

▶ node --version
v15.2.1

It's an honest and easy mistake to make. If the code was this:

function validateURL(url) {
  const url = new URL(url);
  return url.protocol === "https:";
}
// console.log(validateURL("http://www.peterbe.com"));

you'd get this error:

▶ node code2.js
/Users/peterbe/dev/JAVASCRIPT/catching_consts/code2.js:2
  const url = new URL(url);
        ^

SyntaxError: Identifier 'url' has already been declared

which means node refuses to even start it. But it can't with the original code because of the blocking scope that only happens in runtime.

Easiest solution

function validateURL(url) {
  if (url.includes("://")) {
-   const url = new URL(url);
+   const parsedURL = new URL(url);
-   return url.protocol === "https:";
+   return parsedURL.protocol === "https:";
  } else {
    return "dunno";
  }
}
console.log(validateURL("http://www.peterbe.com"));

Best solution

Switch to TypeScript.

▶ cat code.ts
function validateURL(url: string) {
  if (url.includes('://')) {
    const url = new URL(url);
    return url.protocol === 'https:';
  } else {
    return "dunno";
  }
}
console.log(validateURL('http://www.peterbe.com'));

▶ tsc --noEmit --lib es6,dom code.ts
code.ts:3:25 - error TS2448: Block-scoped variable 'url' used before its declaration.

3     const url = new URL(url);
                          ~~~

  code.ts:3:11
    3     const url = new URL(url);
                ~~~
    'url' is declared here.


Found 1 error.