docs: kernel-doc: add support to store output on a YAML file

Add a command line parameter and library support to optionally
store:
- KdocItem intermediate format after parsing;
- man pages output;
- rst output.

inside a YAML file.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Message-ID: <ba54277b3c909867153b9547dfa33c1831ca35d9.1773823995.git.mchehab+huawei@kernel.org>

tools/lib/python/kdoc/kdoc_parser.py

@@ -246,12 +246,13 @@ class KernelDoc:
     #: String to write when a parameter is not described.
     undescribed = "-- undescribed --"
 
-    def __init__(self, config, fname, xforms):
+    def __init__(self, config, fname, xforms, store_src=False):
         """Initialize internal variables"""
 
         self.fname = fname
         self.config = config
         self.xforms = xforms
+        self.store_src = store_src
 
         tokenizer_set_log(self.config.log, f"{self.fname}: CMatch: ")
 
@@ -264,6 +265,9 @@ class KernelDoc:
         # Place all potential outputs into an array
         self.entries = []
 
+        # When store_src is true, the kernel-doc source content is stored here
+        self.source = None
+
         #
         # We need Python 3.7 for its "dicts remember the insertion
         # order" guarantee
@@ -1592,6 +1596,15 @@ class KernelDoc:
         state.DOCBLOCK:			process_docblock,
         }
 
+    def get_source(self):
+        """
+        Return the file content of the lines handled by kernel-doc at the
+        latest parse_kdoc() run.
+
+        Returns none if KernelDoc() was not initialized with store_src,
+        """
+        return self.source
+
     def parse_kdoc(self):
         """
         Open and process each line of a C source file.
@@ -1605,6 +1618,8 @@ class KernelDoc:
         prev = ""
         prev_ln = None
         export_table = set()
+        self.source = []
+        self.state = state.NORMAL
 
         try:
             with open(self.fname, "r", encoding="utf8",
@@ -1631,6 +1646,8 @@ class KernelDoc:
                                           ln, state.name[self.state],
                                           line)
 
+                    prev_state = self.state
+
                     # This is an optimization over the original script.
                     # There, when export_file was used for the same file,
                     # it was read twice. Here, we use the already-existing
@@ -1641,6 +1658,14 @@ class KernelDoc:
                         # Hand this line to the appropriate state handler
                         self.state_actions[self.state](self, ln, line)
 
+                    if self.store_src and prev_state != self.state or self.state != state.NORMAL:
+                        if self.state == state.NAME:
+                            # A "/**" was detected. Add a new source element
+                            self.source.append({"ln": ln, "data": line + "\n"})
+                        else:
+                            # Append to the existing one
+                            self.source[-1]["data"] += line + "\n"
+
             self.emit_unused_warnings()
 
         except OSError: