yozlet · October 8, 2022 16:54
diff --git a/example-graphql-README.md b/example-graphql-README.md
diff --git a/example.graphql b/example.graphql
 {
  
  # Here's the list of organization IDs.
  # I don't know if there's a limit to these lists.
  # Any time you see a plural ("nodes") it *usually* means we're
  # about to loop over a result set. But I think this is implementer
  # convention; "nodes" and "edges" are GraphQL reserved words, but
  # most of the rest aren't.
  # For the moment, I've only put two organization IDs in here.
  nodes(ids: ["MDEyOk9yZ2FuaXphdGlvbjYyMzM5OTQ=", "MDEyOk9yZ2FuaXphdGlvbjY0MzA3MA=="]) {
    
    # Join to a nested list of organization objects.
    id
    ... on Organization {
      name # The organization name

      # Further nesting: Repos.
      # Only asking for 100 because that's a GitHub-set limit.
      # When you want to filter the set of objects returned, it
      # seems to be done in this kind of way - as arguments to
      # the node list. So here, we're filtering for public repos.
      repositories(first: 100, privacy: PUBLIC) {
        nodes {
          
          # Metadata about the repos. I'm only fetching a few values
          # but I could, in theory, go wild with sub-queries about
          # contributors, pull requests, etc.
          # This is ALL coming back in this ONE query.
          name
          createdAt
          url
          homepageUrl
          languages(first:5) {
            nodes {
              name
            }
          }
          pullRequests(first:5, states:[OPEN]) {
            nodes {
              author {
              	login
              }
              title
            }
          }
        }
      }
    }
  }
  
  # All the useful repo data is up above.
  # This following section is cost data about the query itself.
  # The GitHub GraphQL API gives API users a limited hourly budget,
  # in "points", to stop the system being overloaded. Every time 
  # you execute a query, it subtracts the cost from your remaining 
  # budget for the hour.
  
  # If you're experimenting with big queries, I recommend adding
  # this block to the *beginning* of your query, so you can keep
  # an eye on things. Remember that a low query cost becomes a 
  # problem when you're doing a few hundred of these an hour.
  # For more information: https://developer.github.com/v4/guides/resource-limitations/
  
  rateLimit {
    limit     # Your maximum budget. Your budget is reset to this every hour.
    cost      # The cost of this query.
    remaining # How much of your API budget remains.
    resetAt   # The time (in UTC epoch seconds) when your budget will reset.
  }
 }

 # If it wasn't for the 100-node-per-list limit, we'd be able to get
 # *all* the repos for each organization with this query. Instead,
 # we need to do a series of queries which page through the repos,
 # a hundred at a time. However, note that we're actually getting 200
 # repos back with this query - 100 per org. So the current plan is
 # to provide the org IDs for each gov org in GitHub (30 or so) and
 # list them all in the query, so we get up to 3000 repos back.
 #
 # So it's kind of horizontally-slicing across the org structure.
 #
 # (We've had some conversations with GitHub folks and they say that
 # this kind of query behaviour is fine, as long as we keep an eye
 # on our query cost limits.)

 # Future work:
 #
 # Would it be possible to provide the list of organization IDs in
 # a GraphQL variable rather than hardcoded into the query?
diff --git a/nocomments-example.graphql b/nocomments-example.graphql
 {
  nodes(ids: ["MDEyOk9yZ2FuaXphdGlvbjYyMzM5OTQ=", "MDEyOk9yZ2FuaXphdGlvbjY0MzA3MA=="]) {
    id
    ... on Organization {
      name
      
      repositories(first: 100, privacy: PUBLIC) {
        nodes {
          name
          createdAt
          url
          homepageUrl
          languages(first:5) {
            nodes {
              name
            }
          }
          pullRequests(first:5, states:[OPEN]) {
            nodes {
              author {
              	login
              }
              title
            }
          }
        }
      }
    }
  }
  
  rateLimit {
    limit
    cost
    remaining
    resetAt
  }
 }
	{

	# Here's the list of organization IDs.
	# I don't know if there's a limit to these lists.
	# Any time you see a plural ("nodes") it usually means we're
	# about to loop over a result set. But I think this is implementer
	# convention; "nodes" and "edges" are GraphQL reserved words, but
	# most of the rest aren't.
	# For the moment, I've only put two organization IDs in here.
	nodes(ids: ["MDEyOk9yZ2FuaXphdGlvbjYyMzM5OTQ=", "MDEyOk9yZ2FuaXphdGlvbjY0MzA3MA=="]) {

	# Join to a nested list of organization objects.
	id
	... on Organization {
	name # The organization name

	# Further nesting: Repos.
	# Only asking for 100 because that's a GitHub-set limit.
	# When you want to filter the set of objects returned, it
	# seems to be done in this kind of way - as arguments to
	# the node list. So here, we're filtering for public repos.
	repositories(first: 100, privacy: PUBLIC) {
	nodes {

	# Metadata about the repos. I'm only fetching a few values
	# but I could, in theory, go wild with sub-queries about
	# contributors, pull requests, etc.
	# This is ALL coming back in this ONE query.
	name
	createdAt
	url
	homepageUrl
	languages(first:5) {
	nodes {
	name
	}
	}
	pullRequests(first:5, states:[OPEN]) {
	nodes {
	author {
	login
	}
	title
	}
	}
	}
	}
	}
	}

	# All the useful repo data is up above.
	# This following section is cost data about the query itself.
	# The GitHub GraphQL API gives API users a limited hourly budget,
	# in "points", to stop the system being overloaded. Every time
	# you execute a query, it subtracts the cost from your remaining
	# budget for the hour.

	# If you're experimenting with big queries, I recommend adding
	# this block to the beginning of your query, so you can keep
	# an eye on things. Remember that a low query cost becomes a
	# problem when you're doing a few hundred of these an hour.
	# For more information: https://developer.github.com/v4/guides/resource-limitations/

	rateLimit {
	limit # Your maximum budget. Your budget is reset to this every hour.
	cost # The cost of this query.
	remaining # How much of your API budget remains.
	resetAt # The time (in UTC epoch seconds) when your budget will reset.
	}
	}

	# If it wasn't for the 100-node-per-list limit, we'd be able to get
	# all the repos for each organization with this query. Instead,
	# we need to do a series of queries which page through the repos,
	# a hundred at a time. However, note that we're actually getting 200
	# repos back with this query - 100 per org. So the current plan is
	# to provide the org IDs for each gov org in GitHub (30 or so) and
	# list them all in the query, so we get up to 3000 repos back.
	#
	# So it's kind of horizontally-slicing across the org structure.
	#
	# (We've had some conversations with GitHub folks and they say that
	# this kind of query behaviour is fine, as long as we keep an eye
	# on our query cost limits.)

	# Future work:
	#
	# Would it be possible to provide the list of organization IDs in
	# a GraphQL variable rather than hardcoded into the query?