bidi2pdf 0.1.21 → 0.1.22

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 93fc35bee7628afb6627782be91a2fc62caf14f8f365929c166f133d74adebfc
-  data.tar.gz: ca9381a65bd24341c2e486f34fd47f920fbf996e540c54fb421129c2f175f29e
+  metadata.gz: '008d5b0569ba4b7f8bbcd4092da72ce14e5d0e42589a97813f7c64c8bc6a0d9f'
+  data.tar.gz: 8266f91bfa7606d843bed392cee203060cc3b13d98435cc9a0c4a679b5041285
 SHA512:
-  metadata.gz: a457600c1c6a638ee87a28d4f6221918b754a065d6d07acef9e057a4a6a3dce7c0411947cf2c340cb0a5e0ff62171bd9e934f65ca9bd15d9d514f754de11746c
-  data.tar.gz: 383a01704a6871e5e5aafcd7fdd7a97e499009fb7cba63e13adfe2f08c91ba190b78a9d2117e02fd22de1381686c61ab1c94f43fb2d6b6e92e45c9365cfb5122
+  metadata.gz: 27ce2475fa8d30bc9c5447353767c6d2c06db59f57daa7fab7e7a337e26703cc1a0df04439d2b8b68455e5a872138775321a7f31988beb02dba47df0dd06d48d
+  data.tar.gz: acb216b0c656916ee8e8ea797b1fccd026c67fa6260ac5f230f1c44190ffb00455fd83efb5238826c97af0f0051cf68a7335d09e51e0aaa25b85c2efdc802290

data/CHANGELOG.md

@@ -8,10 +8,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-[unreleased]: https://github.com/dieter-medium/bidi2pdf/compare/v0.1.21..HEAD
+[unreleased]: https://github.com/dieter-medium/bidi2pdf/compare/v0.1.22..HEAD
 
 <!-- generated by git-cliff end -->
 
+## [0.1.22] - 2026-10-11
+
+### 🐛 Fixed
+- Report a network-idle timeout as a timeout
+- Let the network-idle wait time out cleanly
+
+### 🔄 Changed
+- Merge pull request #164 from dieter-medium/fix/network-idle-timeout
+- Merge pull request #163 from dieter-medium/feat/disable-script-execution
+
+### 🚀 Added
+- Let a tab switch off script execution
+
 ## [0.1.21] - 2026-10-09
 
 ### 🐛 Fixed
@@ -555,7 +568,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### 🔄 Released
 
-- [unreleased](https://github.com/dieter-medium/bidi2pdf/compare/v0.1.21..HEAD)
+- [unreleased](https://github.com/dieter-medium/bidi2pdf/compare/v0.1.22..HEAD)
+- [0.1.22](https://github.com/dieter-medium/bidi2pdf/compare/v0.1.21..v0.1.22)
 - [0.1.21](https://github.com/dieter-medium/bidi2pdf/compare/v0.1.20..v0.1.21)
 - [0.1.20](https://github.com/dieter-medium/bidi2pdf/compare/v0.1.19..v0.1.20)
 - [0.1.19](https://github.com/dieter-medium/bidi2pdf/compare/v0.1.18..v0.1.19)

data/README.md

@@ -347,6 +347,9 @@ tab.navigate_to "https://example.com/invoice/14432423"
 # or inline
 # tab.inject_style content: "body { background-color: red; }"
 
+# Printing HTML you do not trust? Switch its scripts off before navigating:
+# tab.disable_script_execution
+
 tab.wait_until_network_idle
 tab.print("my.pdf")
 

data/lib/bidi2pdf/bidi/browser_tab.rb

@@ -334,15 +334,20 @@ module Bidi2pdf
         end
       end
 
-      # Waits until the network is idle in the browser tab.
+      # Waits until the network is idle in the browser tab. A timeout does not raise: the
+      # network_idle.bidi2pdf event then carries +timed_out: true+, so subscribers never report a busy
+      # page as idle.
       #
       # @param [Integer] timeout The timeout duration in seconds. Defaults to 10.
       # @param [Float] poll_interval The polling interval in seconds. Defaults to 0.1.
+      # @return [Symbol] :idle or :timeout
       def wait_until_network_idle(timeout: 10, poll_interval: 0.1)
         Bidi2pdf.notification_service.instrument("network_idle.bidi2pdf") do |instrumentation_payload|
-          network_events.wait_until_network_idle(timeout: timeout, poll_interval: poll_interval)
+          status = network_events.wait_until_network_idle(timeout: timeout, poll_interval: poll_interval)
 
           instrumentation_payload[:requests] = network_events.all_events.dup
+          instrumentation_payload[:timed_out] = status == :timeout
+          status
         end
       end
 
@@ -496,6 +501,18 @@ module Bidi2pdf
         client.send_cmd_and_wait(cmd) { |response| response }
       end
 
+      # Switches JavaScript off (or on again) for this tab, through Chrome's own
+      # Emulation.setScriptExecutionDisabled (CDP, via goog:cdp.sendCommand). Call it before
+      # navigating: it holds for every later navigation in the tab, so a page printed from untrusted
+      # HTML runs none of its scripts.
+      #
+      # @param [Boolean] disabled Defaults to true.
+      def disable_script_execution(disabled: true)
+        cmd = Commands::CdpSendCommand.new(method: "Emulation.setScriptExecutionDisabled", params: { value: disabled },
+                                           session: cdp_session)
+        client.send_cmd_and_wait(cmd) { |response| response }
+      end
+
       private
 
       def build_command_and_extractor(print_options)

data/lib/bidi2pdf/bidi/network_events.rb

@@ -95,24 +95,33 @@ module Bidi2pdf
         end
       end
 
+      # Waits until no request is in flight, or until +timeout+ seconds passed.
+      #
+      # @return [Symbol] :idle when every request completed, :timeout when some were still open -
+      #   it never raises for a timeout, so a caller decides whether a busy page is good enough.
       def wait_until_network_idle(timeout: 10, poll_interval: 0.01)
         start_time = Time.now
 
         loop do
           unless events.values.any?(&:in_progress?)
             Bidi2pdf.logger.debug "✅ All network events completed."
-            break
+            return :idle
           end
 
           if Time.now - start_time > timeout
-            Bidi2pdf.logger.warn "⏰ Timeout while waiting for network events to complete. Still in progress: #{in_progress.map(&:id)}"
-            # rubocop:enable Layout/LineLength
-            break
+            log_idle_timeout
+            return :timeout
           end
 
           sleep(poll_interval)
         end
       end
+
+      # Names the requests still open when the wait gives up - it carries on, it does not raise.
+      def log_idle_timeout
+        in_progress = events.values.select(&:in_progress?)
+        Bidi2pdf.logger.warn "⏰ Timeout while waiting for network events to complete. Still in progress: #{in_progress.map(&:id)}"
+      end
     end
   end
 end

data/lib/bidi2pdf/notifications/json_subscriber.rb

@@ -53,8 +53,9 @@ module Bidi2pdf
         write(event: "page_loaded")
       end
 
-      def on_network_idle(_event)
-        write(event: "network_idle")
+      # A wait that timed out is its own event: a consumer reading "network_idle" can trust it.
+      def on_network_idle(event)
+        write(event: event.payload[:timed_out] ? "network_idle_timeout" : "network_idle")
       end
 
       def on_console(event)

data/lib/bidi2pdf/notifications/logging_subscriber.rb

@@ -61,7 +61,7 @@ module Bidi2pdf
       def network_idle(event)
         return unless logger.info?
 
-        requests = event.payload[:requests]
+        requests = event.payload[:requests] || []
         transfered = requests.map { |request| request.bytes_received || 0 }.sum
         status_counts = requests
                           .group_by { |evt| evt.http_status_code || 0 }
@@ -70,8 +70,12 @@ module Bidi2pdf
                           .map { |code, count| "#{code}: #{count}" }
                           .join(", ")
 
-        logger.info "Network was idle after #{event.duration.round(1)}ms, #{requests.size} requests, " \
-                      "transferred #{transfered} bytes (status codes: #{status_counts})"
+        summary = "#{requests.size} requests, transferred #{transfered} bytes (status codes: #{status_counts})"
+        if event.payload[:timed_out]
+          logger.warn "Network was still busy after #{event.duration.round(1)}ms (timed out), #{summary}"
+        else
+          logger.info "Network was idle after #{event.duration.round(1)}ms, #{summary}"
+        end
       end
 
       # rubocop:enable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity

data/lib/bidi2pdf/schema.rb

@@ -196,7 +196,8 @@ module Bidi2pdf
       "properties" => {
         "schema_version" => { "const" => 1 },
         "t_ms" => { "type" => "integer", "description" => "milliseconds since the render started" },
-        "event" => { "type" => "string", "enum" => %w[navigate page_loaded network_idle console print screenshot result] },
+        "event" => { "type" => "string", "enum" => %w[navigate page_loaded network_idle network_idle_timeout console print screenshot result],
+                     "description" => "network_idle_timeout: the wait for an idle network gave up with requests still open" },
         "url" => { "type" => "string", "description" => "present on a navigate event" },
         "level" => { "type" => "string", "description" => "present on a console event" },
         "text" => { "type" => "string", "description" => "present on a console event" },

data/lib/bidi2pdf/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Bidi2pdf
-  VERSION = "0.1.21"
+  VERSION = "0.1.22"
 end

data/sig/bidi2pdf/bidi/browser_tab.rbs

@@ -169,10 +169,13 @@ module Bidi2pdf
       # @return [Object] The result from the style creation promise.
       def inject_style: (?url: untyped?, ?content: untyped?, ?id: untyped?) -> untyped
 
-      # Waits until the network is idle in the browser tab.
+      # Waits until the network is idle in the browser tab. A timeout does not raise: the
+      # network_idle.bidi2pdf event then carries +timed_out: true+, so subscribers never report a busy
+      # page as idle.
       #
       # @param [Integer] timeout The timeout duration in seconds. Defaults to 10.
       # @param [Float] poll_interval The polling interval in seconds. Defaults to 0.1.
+      # @return [Symbol] :idle or :timeout
       def wait_until_network_idle: (?timeout: ::Integer, ?poll_interval: ::Float) -> untyped
 
       # Waits until the page is fully loaded in the browser tab.
@@ -227,6 +230,14 @@ module Bidi2pdf
       # @param [Float, nil] device_pixel_ratio Defaults to nil (browser default).
       def set_viewport: (width: untyped, height: untyped, ?device_pixel_ratio: untyped?) -> untyped
 
+      # Switches JavaScript off (or on again) for this tab, through Chrome's own
+      # Emulation.setScriptExecutionDisabled (CDP, via goog:cdp.sendCommand). Call it before
+      # navigating: it holds for every later navigation in the tab, so a page printed from untrusted
+      # HTML runs none of its scripts.
+      #
+      # @param [Boolean] disabled Defaults to true.
+      def disable_script_execution: (?disabled: bool) -> untyped
+
       private
 
       def build_command_and_extractor: (untyped print_options) -> ::Array[untyped]

data/sig/bidi2pdf/bidi/network_events.rbs

@@ -24,7 +24,14 @@ module Bidi2pdf
 
       def log_network_traffic: (?format: ::Symbol) -> untyped
 
-      def wait_until_network_idle: (?timeout: ::Integer, ?poll_interval: ::Float) -> untyped
+      # Waits until no request is in flight, or until +timeout+ seconds passed.
+      #
+      # @return [Symbol] :idle when every request completed, :timeout when some were still open -
+      #   it never raises for a timeout, so a caller decides whether a busy page is good enough.
+      def wait_until_network_idle: (?timeout: ::Integer, ?poll_interval: ::Float) -> (:idle | :timeout | untyped)
+
+      # Names the requests still open when the wait gives up - it carries on, it does not raise.
+      def log_idle_timeout: () -> untyped
     end
   end
 end

data/sig/bidi2pdf/notifications/json_subscriber.rbs

@@ -31,7 +31,8 @@ module Bidi2pdf
 
       def on_page_loaded: (untyped _event) -> untyped
 
-      def on_network_idle: (untyped _event) -> untyped
+      # A wait that timed out is its own event: a consumer reading "network_idle" can trust it.
+      def on_network_idle: (untyped event) -> untyped
 
       def on_console: (untyped event) -> untyped
 

data/sig/bidi2pdf/schema.rbs

@@ -26,7 +26,7 @@ module Bidi2pdf
 
     MANIFEST: { "$schema" => "https://json-schema.org/draft/2020-12/schema", "title" => "Bidi2pdf render manifest", "description" => "--manifest FILE output", "type" => "object", "required" => ::Array["schema_version" | "bidi2pdf_version" | "created_at" | "input" | "output" | "navigation" | "render"], "properties" => { "schema_version" => { "const" => 1 }, "bidi2pdf_version" => { "type" => "string" }, "created_at" => { "type" => "string", "format" => "date-time" }, "input" => { "type" => "object", "required" => ::Array["type"], "properties" => { "type" => { "type" => "string", "enum" => ::Array["url" | "html_file" | "stdin"] }, "url" => { "type" => ::Array["string" | "null"] } } }, "output" => { "type" => "object", "properties" => { "path" => { "type" => ::Array["string" | "null"] }, "pages" => { "type" => ::Array["integer" | "null"] }, "bytes" => { "type" => ::Array["integer" | "null"] }, "sha256" => { "type" => ::Array["string" | "null"] } } }, "browser" => { "type" => "object" }, "navigation" => untyped, "render" => { "type" => "object", "properties" => { "duration_ms" => { "type" => ::Array["integer" | "null"] } } }, "console" => untyped, "network_failures" => untyped, "warnings" => untyped, "headers" => { "type" => "object", "description" => "present only when custom headers were given; secret-bearing values are redacted" } } }
 
-    EVENT: { "$schema" => "https://json-schema.org/draft/2020-12/schema", "title" => "Bidi2pdf --json-stream event", "description" => "one JSON object per stderr line while --json-stream is active. In structured mode (--json/--output -), the last line is always {event: \"result\", result: <the matching command's own schema - see \"result\"'s own oneOf>}. In human mode (--json-stream given alone), only progress events are emitted - there is no synthetic final \"result\" event, since there is no structured result being built; the human-readable log is the completion/failure signal.", "type" => "object", "required" => ::Array["schema_version" | "t_ms" | "event"], "properties" => { "schema_version" => { "const" => 1 }, "t_ms" => { "type" => "integer", "description" => "milliseconds since the render started" }, "event" => { "type" => "string", "enum" => ::Array["navigate" | "page_loaded" | "network_idle" | "console" | "print" | "screenshot" | "result"] }, "url" => { "type" => "string", "description" => "present on a navigate event" }, "level" => { "type" => "string", "description" => "present on a console event" }, "text" => { "type" => "string", "description" => "present on a console event" }, "result" => { "description" => "present only on the final \"result\" event (structured mode only); shape depends on which command produced this stream - each branch's own \"command\" value disambiguates", "oneOf" => ::Array[untyped] } } }
+    EVENT: { "$schema" => "https://json-schema.org/draft/2020-12/schema", "title" => "Bidi2pdf --json-stream event", "description" => "one JSON object per stderr line while --json-stream is active. In structured mode (--json/--output -), the last line is always {event: \"result\", result: <the matching command's own schema - see \"result\"'s own oneOf>}. In human mode (--json-stream given alone), only progress events are emitted - there is no synthetic final \"result\" event, since there is no structured result being built; the human-readable log is the completion/failure signal.", "type" => "object", "required" => ::Array["schema_version" | "t_ms" | "event"], "properties" => { "schema_version" => { "const" => 1 }, "t_ms" => { "type" => "integer", "description" => "milliseconds since the render started" }, "event" => { "type" => "string", "enum" => ::Array["navigate" | "page_loaded" | "network_idle" | "network_idle_timeout" | "console" | "print" | "screenshot" | "result"], "description" => "network_idle_timeout: the wait for an idle network gave up with requests still open" }, "url" => { "type" => "string", "description" => "present on a navigate event" }, "level" => { "type" => "string", "description" => "present on a console event" }, "text" => { "type" => "string", "description" => "present on a console event" }, "result" => { "description" => "present only on the final \"result\" event (structured mode only); shape depends on which command produced this stream - each branch's own \"command\" value disambiguates", "oneOf" => ::Array[untyped] } } }
 
     RECIPE_SOURCE: { "description" => "exactly one of url, file, stdin", "oneOf" => ::Array[{ "type" => "object", "required" => ::Array["url"], "properties" => { "url" => { "type" => "string" } }, "additionalProperties" => false } | { "type" => "object", "required" => ::Array["file"], "properties" => { "file" => { "type" => "string" } }, "additionalProperties" => false } | { "type" => "object", "required" => ::Array["stdin"], "properties" => { "stdin" => { "const" => true } }, "additionalProperties" => false }] }
 

data/sig/bidi2pdf/version.rbs

@@ -1,3 +1,3 @@
 module Bidi2pdf
-  VERSION: "0.1.21"
+  VERSION: "0.1.22"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bidi2pdf
 version: !ruby/object:Gem::Version
-  version: 0.1.21
+  version: 0.1.22
 platform: ruby
 authors:
 - Dieter S.