From d1fc38488c4b784550f4ca4dbbc7fc9b85149464 Mon Sep 17 00:00:00 2001 From: Phil Rzewski Date: Thu, 20 Aug 2026 17:36:01 -0700 Subject: [PATCH] Point Zeek links in docs at new locations and exclude them from link checker --- .linkspector.yml | 6 ++++ book/src/command/formats.md | 2 +- book/src/dev/integrations/zeek/logs.md | 6 ++-- book/src/dev/integrations/zeek/shaping.md | 2 +- book/src/dev/integrations/zeek/types.md | 36 +++++++++++------------ 5 files changed, 29 insertions(+), 23 deletions(-) diff --git a/.linkspector.yml b/.linkspector.yml index c3800f90f6..b3cd9e18d4 100644 --- a/.linkspector.yml +++ b/.linkspector.yml @@ -3,6 +3,7 @@ dirs: useGitIgnore: true excludedDirs: - node_modules +userAgent: 'linkspector (+https://github.com/brimdata/super; docs link check)' ignorePatterns: @@ -19,3 +20,8 @@ ignorePatterns: # Not crawling the following due to persistent HTTP 503 errors - pattern: '^https://sqlite.org' + +# Not crawling the following due to a Cloudflare challenge that causes HTTP +# 429/403 errors during link checking +# See https://github.com/zeek/zeek/issues/5819 + - pattern: '^https://docs\.zeek\.org' diff --git a/book/src/command/formats.md b/book/src/command/formats.md index e883149cde..b6907e8955 100644 --- a/book/src/command/formats.md +++ b/book/src/command/formats.md @@ -13,7 +13,7 @@ The supported [input](input.md) and [output](output.md) formats include the foll | `parquet` | yes | `.parquet` | [Apache Parquet](https://github.com/apache/parquet-format) | | `sup` | yes | `.sup` | [SUP](../formats/sup.md) | | `tsv` | yes | `.tsv` | [Tab-Separated Values](https://en.wikipedia.org/wiki/Tab-separated_values) | -| `zeek` | yes | `.zeek` | [Zeek Logs](https://docs.zeek.org/en/current/logs/index.html) | +| `zeek` | yes | `.zeek` | [Zeek Logs](https://docs.zeek.org/en/current/reference/logs/index.html) | >[!NOTE] > Best performance is typically achieved when operating on data in binary columnar formats diff --git a/book/src/dev/integrations/zeek/logs.md b/book/src/dev/integrations/zeek/logs.md index 2e5ba74ed9..4eea066564 100644 --- a/book/src/dev/integrations/zeek/logs.md +++ b/book/src/dev/integrations/zeek/logs.md @@ -4,12 +4,12 @@ SuperDB can read both of the common Zeek log formats. This section provides guidance for what to expect when reading logs of these formats using the [super](../../../command/super.md) command. -[Zeek TSV](https://docs.zeek.org/en/current/log-formats.html#zeek-log-formats) +[Zeek TSV](https://docs.zeek.org/en/current/tutorial/logs.html#zeek-log-formats) is Zeek's default output format for logs. This format can be read automatically (i.e., no `-i` command line flag is necessary to indicate the input format) with [super](../../../command/super.md). s -The following example shows a TSV [conn.log](https://docs.zeek.org/en/current/logs/conn.html) being read via `super` and +The following example shows a TSV [conn.log](https://docs.zeek.org/en/current/reference/logs/conn.html) being read via `super` and output as [Super (SUP)](../../../formats/sup.md). ## conn.log @@ -74,7 +74,7 @@ equivalent [super-structured types](../../../formats/model.md#1-primitive-types) ## The Role of `_path` Zeek's `_path` field plays an important role in differentiating between its -different [log types](https://docs.zeek.org/en/current/script-reference/log-files.html) +different [log types](https://docs.zeek.org/en/current/reference/zeekscript/log-files.html) (`conn`, `dns`, etc.) For instance, [shaping Zeek JSON](shaping.md) relies on the value of the `_path` field to know which type to apply to an input JSON diff --git a/book/src/dev/integrations/zeek/shaping.md b/book/src/dev/integrations/zeek/shaping.md index 63360cb8aa..fbd7c1673d 100644 --- a/book/src/dev/integrations/zeek/shaping.md +++ b/book/src/dev/integrations/zeek/shaping.md @@ -105,7 +105,7 @@ fields or keep them while assigning inferred types. ## Reference Shaper Contents The following reference `shaper.spq` may seem large, but ultimately it follows a -fairly simple pattern that repeats across the many [Zeek log types](https://docs.zeek.org/en/current/script-reference/log-files.html). +fairly simple pattern that repeats across the many [Zeek log types](https://docs.zeek.org/en/current/reference/zeekscript/log-files.html). ```mdtest-input shaper.spq -- This reference shaper for Zeek JSON logs was most recently tested with diff --git a/book/src/dev/integrations/zeek/types.md b/book/src/dev/integrations/zeek/types.md index 046b149cd6..9d4f9d7f73 100644 --- a/book/src/dev/integrations/zeek/types.md +++ b/book/src/dev/integrations/zeek/types.md @@ -1,7 +1,7 @@ # Type System As the [super-structured data model](../../../formats/model.md) was in many ways inspired by the -[Zeek TSV log format](https://docs.zeek.org/en/current/log-formats.html#zeek-log-formats), +[Zeek TSV log format](https://docs.zeek.org/en/current/tutorial/logs.html#zeek-log-formats), SuperDB's rich storage formats ([SUP](../../../formats/sup.md), [CSUP](../../../formats/csup.md), etc.) maintain comprehensive interoperability with Zeek. @@ -25,7 +25,7 @@ when output as SUP. ## Equivalent Types The following table summarizes which Zed data type corresponds to each -[Zeek data type](https://docs.zeek.org/en/current/script-reference/types.html) +[Zeek data type](https://docs.zeek.org/en/current/reference/zeekscript/types.html) that may appear in a Zeek TSV log. While most types have a simple 1-to-1 mapping from Zeek to Zed and back to Zeek again, the sections linked from the **Additional Detail** column describe cosmetic differences and other subtleties @@ -33,25 +33,25 @@ applicable to handling certain types. | Zeek Type | Zed Type | Additional Detail | |------------|------------|-------------------| -| [`bool`](https://docs.zeek.org/en/current/script-reference/types.html#type-bool) | [`bool`](../../../formats/model.md#1-primitive-types) | | -| [`count`](https://docs.zeek.org/en/current/script-reference/types.html#type-count) | [`uint64`](../../../formats/model.md#1-primitive-types) | | -| [`int`](https://docs.zeek.org/en/current/script-reference/types.html#type-int) | [`int64`](../../../formats/model.md#1-primitive-types) | | -| [`double`](https://docs.zeek.org/en/current/script-reference/types.html#type-double) | [`float64`](../../../formats/model.md#1-primitive-types) | See [`double` details](#double) | -| [`time`](https://docs.zeek.org/en/current/script-reference/types.html#type-time) | [`time`](../../../formats/model.md#1-primitive-types) | | -| [`interval`](https://docs.zeek.org/en/current/script-reference/types.html#type-interval) | [`duration`](../../../formats/model.md#1-primitive-types) | | -| [`string`](https://docs.zeek.org/en/current/script-reference/types.html#type-string) | [`string`](../../../formats/model.md#1-primitive-types) | See [`string` details about escaping](#string) | -| [`port`](https://docs.zeek.org/en/current/script-reference/types.html#type-port) | [`uint16`](../../../formats/model.md#1-primitive-types) | See [`port` details](#port) | -| [`addr`](https://docs.zeek.org/en/current/script-reference/types.html#type-addr) | [`ip`](../../../formats/model.md#1-primitive-types) | | -| [`subnet`](https://docs.zeek.org/en/current/script-reference/types.html#type-subnet) | [`net`](../../../formats/model.md#1-primitive-types) | | -| [`enum`](https://docs.zeek.org/en/current/script-reference/types.html#type-enum) | [`string`](../../../formats/model.md#1-primitive-types) | See [`enum` details](#enum) | -| [`set`](https://docs.zeek.org/en/current/script-reference/types.html#type-set) | [`set`](../../../formats/model.md#23-set) | See [`set` details](#set) | -| [`vector`](https://docs.zeek.org/en/current/script-reference/types.html#type-vector) | [`array`](../../../formats/model.md#22-array) | | -| [`record`](https://docs.zeek.org/en/current/script-reference/types.html#type-record) | [`record`](../../../formats/model.md#21-record) | See [`record` details](#record) | +| [`bool`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-bool) | [`bool`](../../../formats/model.md#1-primitive-types) | | +| [`count`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-count) | [`uint64`](../../../formats/model.md#1-primitive-types) | | +| [`int`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-int) | [`int64`](../../../formats/model.md#1-primitive-types) | | +| [`double`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-double) | [`float64`](../../../formats/model.md#1-primitive-types) | See [`double` details](#double) | +| [`time`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-time) | [`time`](../../../formats/model.md#1-primitive-types) | | +| [`interval`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-interval) | [`duration`](../../../formats/model.md#1-primitive-types) | | +| [`string`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-string) | [`string`](../../../formats/model.md#1-primitive-types) | See [`string` details about escaping](#string) | +| [`port`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-port) | [`uint16`](../../../formats/model.md#1-primitive-types) | See [`port` details](#port) | +| [`addr`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-addr) | [`ip`](../../../formats/model.md#1-primitive-types) | | +| [`subnet`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-subnet) | [`net`](../../../formats/model.md#1-primitive-types) | | +| [`enum`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-enum) | [`string`](../../../formats/model.md#1-primitive-types) | See [`enum` details](#enum) | +| [`set`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-set) | [`set`](../../../formats/model.md#23-set) | See [`set` details](#set) | +| [`vector`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-vector) | [`array`](../../../formats/model.md#22-array) | | +| [`record`](https://docs.zeek.org/en/current/reference/zeekscript/types.html#type-record) | [`record`](../../../formats/model.md#21-record) | See [`record` details](#record) | >[!NOTE] -> The [Zeek data types](https://docs.zeek.org/en/current/script-reference/types.html) +> The [Zeek data types](https://docs.zeek.org/en/current/reference/zeekscript/types.html) > page describes the types in the context of the -> [Zeek scripting language](https://docs.zeek.org/en/current/scripting/index.html). +> [Zeek scripting language](https://docs.zeek.org/en/current/tutorial/scripting/index.html). > The Zeek types available in scripting are a superset of the data types that > may appear in Zeek log files. The encodings of the types also differ in some > ways between the two contexts. However, we link to this reference because