[pkg/stanza] Adopt semantic convention for the log file path attribute (

#37210)

#### Description

This PR adopts [the semantic convention for the log file path
attribute](https://github.com/open-telemetry/semantic-conventions/blob/main/docs/general/logs.md#log-file),
which should be `attributes["log.file.path"]`.

It fixes the default value for the `recombine` operator's
`source_identifier`.

.chloggen/semantic_source_identifier.yaml

@@ -0,0 +1,28 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: bug_fix
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: pkg/stanza
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Fix default source identifier in recombine operator
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [37210]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext: |
+  Its defualt value is now aligned with the semantic conventions: `attributes["log.file.path"]`
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [user]

pkg/stanza/docs/operators/recombine.md

@@ -4,22 +4,22 @@ The `recombine` operator combines consecutive logs into single logs based on sim
 
 ### Configuration Fields
 
-| Field                          | Default                    | Description |
-| ---                            | ---                        | ---         |
-| `id`                           | `recombine`                | A unique identifier for the operator. |
-| `output`                       | Next in pipeline           | The connected operator(s) that will receive all outbound entries. |
-| `on_error`                     | `send`                     | The behavior of the operator if it encounters an error. See [on_error](../types/on_error.md). |
-| `is_first_entry`               |                            | An [expression](../types/expression.md) that returns true if the entry being processed is the first entry in a multiline series. |
-| `is_last_entry`                |                            | An [expression](../types/expression.md) that returns true if the entry being processed is the last entry in a multiline series. |
-| `combine_field`                | required                   | The [field](../types/field.md) from all the entries that will be recombined. |
-| `combine_with`                 | `"\n"`                     | The string that is put between the combined entries. This can be an empty string as well. When using special characters like `\n`, be sure to enclose the value in double quotes: `"\n"`. |
-| `max_batch_size`               | 1000                       | The maximum number of consecutive entries that will be combined into a single entry. |
-| `max_unmatched_batch_size`     | 100                        | The maximum number of consecutive entries that will be combined into a single entry before the match occurs (with `is_first_entry` or `is_last_entry`), e.g. `max_unmatched_batch_size=0` - all entries combined, `max_unmatched_batch_size=1` - all entries uncombined until the match occurs, `max_unmatched_batch_size=100` - entries combined into 100-entry-packages until the match occurs  |
-| `overwrite_with`               | `newest`                   | Whether to use the fields from the `oldest` or the `newest` entry for all the fields that are not combined. |
-| `force_flush_period`           | `5s`                       | Flush timeout after which entries will be flushed aborting the wait for their sub parts to be merged with. |
-| `source_identifier`            | `$attributes["file.path"]` | The [field](../types/field.md) to separate one source of logs from others when combining them. |
-| `max_sources`                  | 1000                       | The maximum number of unique sources allowed concurrently to be tracked for combining separately. |
-| `max_log_size`                 | 0                          | The maximum bytes size of the combined field. Once the size exceeds the limit, all received entries of the source will be combined and flushed. "0" of max_log_size means no limit. |
+| Field                          | Default                     | Description |
+| ---                            | ---                         | ---         |
+| `id`                           | `recombine`                 | A unique identifier for the operator. |
+| `output`                       | Next in pipeline            | The connected operator(s) that will receive all outbound entries. |
+| `on_error`                     | `send`                      | The behavior of the operator if it encounters an error. See [on_error](../types/on_error.md). |
+| `is_first_entry`               |                             | An [expression](../types/expression.md) that returns true if the entry being processed is the first entry in a multiline series. |
+| `is_last_entry`                |                             | An [expression](../types/expression.md) that returns true if the entry being processed is the last entry in a multiline series. |
+| `combine_field`                | required                    | The [field](../types/field.md) from all the entries that will be recombined. |
+| `combine_with`                 | `"\n"`                      | The string that is put between the combined entries. This can be an empty string as well. When using special characters like `\n`, be sure to enclose the value in double quotes: `"\n"`. |
+| `max_batch_size`               | 1000                        | The maximum number of consecutive entries that will be combined into a single entry. |
+| `max_unmatched_batch_size`     | 100                         | The maximum number of consecutive entries that will be combined into a single entry before the match occurs (with `is_first_entry` or `is_last_entry`), e.g. `max_unmatched_batch_size=0` - all entries combined, `max_unmatched_batch_size=1` - all entries uncombined until the match occurs, `max_unmatched_batch_size=100` - entries combined into 100-entry-packages until the match occurs  |
+| `overwrite_with`               | `newest`                    | Whether to use the fields from the `oldest` or the `newest` entry for all the fields that are not combined. |
+| `force_flush_period`           | `5s`                        | Flush timeout after which entries will be flushed aborting the wait for their sub parts to be merged with. |
+| `source_identifier`            | attributes["log.file.path"] | The [field](../types/field.md) to separate one source of logs from others when combining them. |
+| `max_sources`                  | 1000                        | The maximum number of unique sources allowed concurrently to be tracked for combining separately. |
+| `max_log_size`                 | 0                           | The maximum bytes size of the combined field. Once the size exceeds the limit, all received entries of the source will be combined and flushed. "0" of max_log_size means no limit. |
 
 Exactly one of `is_first_entry` and `is_last_entry` must be specified.
 

pkg/stanza/operator/input/file/input_test.go

@@ -13,6 +13,7 @@ import (
 	"github.com/stretchr/testify/require"
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/entry"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/fileconsumer/attrs"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/testutil"
 )
 
@@ -62,7 +63,7 @@ func TestAddFileResolvedFields(t *testing.T) {
 
 	e := waitForOne(t, logReceived)
 	require.Equal(t, filepath.Base(symLinkPath), e.Attributes["log.file.name"])
-	require.Equal(t, symLinkPath, e.Attributes["log.file.path"])
+	require.Equal(t, symLinkPath, e.Attributes[attrs.LogFilePath])
 	require.Equal(t, filepath.Base(resolved), e.Attributes["log.file.name_resolved"])
 	require.Equal(t, resolved, e.Attributes["log.file.path_resolved"])
 	if runtime.GOOS != "windows" {

pkg/stanza/operator/parser/container/config.go

@@ -12,14 +12,15 @@ import (
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/entry"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/errors"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/fileconsumer/attrs"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/helper"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/transformer/recombine"
 )
 
 const (
 	operatorType                       = "container"
-	recombineSourceIdentifier          = "log.file.path"
+	recombineSourceIdentifier          = attrs.LogFilePath
 	recombineIsLastEntry               = "attributes.logtag == 'F'"
 	removeOriginalTimeFieldFeatureFlag = "filelog.container.removeOriginalTimeField"
 )

pkg/stanza/operator/parser/container/parser.go

@@ -17,6 +17,7 @@ import (
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal/timeutils"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/entry"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/fileconsumer/attrs"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator"
 	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza/operator/helper"
 )
@@ -30,7 +31,7 @@ const (
 	crioPattern         = "^(?P<time>[^ Z]+) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$"
 	containerdPattern   = "^(?P<time>[^ ^Z]+Z) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$"
 	logpathPattern      = "^.*(\\/|\\\\)(?P<namespace>[^_]+)_(?P<pod_name>[^_]+)_(?P<uid>[a-f0-9\\-]+)(\\/|\\\\)(?P<container_name>[^\\._]+)(\\/|\\\\)(?P<restart_count>\\d+)\\.log$"
-	logPathField        = "log.file.path"
+	logPathField        = attrs.LogFilePath
 	crioTimeLayout      = "2006-01-02T15:04:05.999999999Z07:00"
 	goTimeLayout        = "2006-01-02T15:04:05.999Z"
 )